Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
A skill your agent uses when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or recording meaningful…
$ npx skills add Frappucc1no/recall-loom --skill recallloom -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Frappucc1no/recall-loom recallloom --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Frappucc1no/recall-loom.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/recallloom .claude/skills/recallloom && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "recallloom" agent skill from https://github.com/Frappucc1no/recall-loom/tree/main/skills/recallloom into .claude/skills/recallloom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recallloom", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Frappucc1no/recall-loom/tree/main/skills/recallloomType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Frappucc1no/recall-loom --skill recallloom -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Frappucc1no/recall-loom recallloom --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Frappucc1no/recall-loom.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/recallloom .agents/skills/recallloom && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "recallloom" agent skill from https://github.com/Frappucc1no/recall-loom/tree/main/skills/recallloom into .agents/skills/recallloom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recallloom", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Frappucc1no/recall-loom --skill recallloom -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Frappucc1no/recall-loom recallloom --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Frappucc1no/recall-loom.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/recallloom .cursor/skills/recallloom && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "recallloom" agent skill from https://github.com/Frappucc1no/recall-loom/tree/main/skills/recallloom into .cursor/skills/recallloom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recallloom", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Frappucc1no/recall-loom.git --path skills/recallloom--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Frappucc1no/recall-loom --skill recallloom -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Frappucc1no/recall-loom recallloom --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Frappucc1no/recall-loom.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/recallloom .gemini/skills/recallloom && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "recallloom" agent skill from https://github.com/Frappucc1no/recall-loom/tree/main/skills/recallloom into .gemini/skills/recallloom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recallloom", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Frappucc1no/recall-loom recallloomInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Frappucc1no/recall-loom --skill recallloom -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Frappucc1no/recall-loom.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/recallloom .github/skills/recallloom && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "recallloom" agent skill from https://github.com/Frappucc1no/recall-loom/tree/main/skills/recallloom into .github/skills/recallloom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recallloom", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Frappucc1no/recall-loom --skill recallloom -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Frappucc1no/recall-loom recallloom --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Frappucc1no/recall-loom.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/recallloom .opencode/skills/recallloom && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "recallloom" agent skill from https://github.com/Frappucc1no/recall-loom/tree/main/skills/recallloom into .opencode/skills/recallloom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recallloom", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
recallloomA skill your agent uses when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or recording meaningful…
Recallloom is an agent skill from Frappucc1no/recall-loom. Use when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or recording meaningful progress across sessions. Works best for long-horizon, file-based projects and supports research writing, product document collaboration, software project coordination, and broader cross-functional project continuity.
Its SKILL.md is about 6.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 128 other files, including scripts and reference files (for example `managed-assets.json` and `native_commands/README.md`).
It sits in Agent Workflows, covering Agent memory. The repository describes itself as: Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local project files. The licence is Apache-2.0.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit a103b6d. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Recallloom loads about 6.3k tokens when it runs, and up to ~34k if it reads all its reference files. Until then it costs about 100 tokens; SKILL.md has 3,087 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from Frappucc1no/recall-loom at commit a103b6d, republished under its Apache-2.0 licence (© Frappucc1no). 3,087 words, ~6,269 tokens.
.claude/skills/recallloom/SKILL.md (or your agent's skills folder). This skill also uses 124 other files; get the full folder from GitHub.RecallLoom is a portable context harness for session-based agents.
It provides a lightweight file model for project continuity across sessions without requiring heavy infrastructure.
The goal is not to remember everything. The goal is to keep the right project state durable, readable, and recoverable across sessions.
This file is the agent-facing entrypoint for the installable recallloom/ skill package.
Install and trigger this package through your host agent's normal skill discovery flow. RecallLoom itself does not require a custom host-specific launcher inside the package. The package may still ship optional native wrapper templates for supported hosts.
This installable package is intentionally kept lean. Human-facing repository landing pages and marketing docs may exist upstream, but they are not bundled into the installed skill directory.
In the source repository, README.md and README.en.md are concise public
front doors, README.zh-CN.md is the compatibility entry, INDEX.md is the
full map, and USAGE.md is the operator guide.
Those files describe the same helper contract as this installed package
entrypoint rather than defining a second logic set.
For package inventory, protocol details, and helper-script behavior, rely on the files that ship inside the package itself:
managed-assets.jsonpackage-metadata.jsonreferences/file-contracts.mdreferences/operation-playbooks.mdreferences/package-support-policy.mdreferences/recording-workflow.mdreferences/protocol.md<!-- RecallLoom metadata sync start: package-metadata -->
0.5.01.01.0<!-- RecallLoom metadata sync end: package-metadata -->
<!-- RecallLoom metadata sync start: runtime-assumptions -->
enzh-CNAGENTS.mdCLAUDE.mdGEMINI.md.github/copilot-instructions.md<!-- RecallLoom metadata sync end: runtime-assumptions -->
RecallLoom package support is separate from project sidecar protocol compatibility.
.recallloom/.readonly_only, mutating helpers MUST block while diagnostic and read-only helpers MAY continue.diagnostic_only, only diagnostic helpers SHOULD continue.unknown_offline because no local support cache exists, local diagnostic, read-only, and mutating actions MAY continue; network access is not a prerequisite for local RecallLoom use.supported, upgrade_recommended, readonly_only, or diagnostic_only restriction.invalid_support_advisory remains distinct from an invalid local cache: correct or refresh the advisory rather than treating it as cache damage.blocked_reason: package_support_blocked and a package_support object. See references/package-support-policy.md.allow, warn, ask, or block in helper readiness output when provenance state is relevant.warn is for low-risk structural-only or readable legacy states and should stay brief; repeated same-session low-risk warnings should be cooldown-friendly.ask is for legacy review / repair import or reviewed imported baseline actions and requires explicit operator confirmation before higher-risk writes.block is non-waivable for forged markers, detected receipt/store inconsistency, direct state.json / config.json edits, privacy violations, and any general, legacy, or unbound state classified as inconsistent_or_tampered_evidence.references/operation-playbooks.md.write for managed-file writes, append for daily-log entries, and sync-current-state-after-append only when its post-append contract requires that lane. Do not bypass the dispatcher with blind file replacement, blind patching, or hand-built sidecar files.append; its internal helper writes the entry. Do not handwrite daily-log-entry markers.repair-daily-log-cursor; its internal helper performs the repair. Do not hand-edit state.json.daily_logs.write; its internal helper performs the revision-aware commit. Do not handwrite file-state markers.STORAGE_ROOT/state.json and STORAGE_ROOT/config.json MUST NOT be hand-edited during normal operation.write and append; sync-current-state-after-append is used only when its post-append contract requires that lane. commit_context_file.py and append_daily_log_entry.py are internal dispatcher/integration surfaces: the dispatcher performs its own fresh preflight, constructs the binding, and persists the matching lease immediately before calling a helper. A read-only preflight does not issue either material, there is no independent operator pickup interface, and a hand-invoked helper without dispatcher-issued material is expected to fail. For the first write from a reviewed imported baseline, use dispatcher write or append with --confirm-review-imported-baseline; the post-append sync lane also accepts that confirmation when its contract requires it. The internal helpers do not accept the flag and only consume dispatcher-issued confirmation-bound binding and lease material.1.0 daily-log counters are file-local: entry-seq is 1..N within one daily log and canonical entry-id is entry-{entry_seq}. Do not treat either as globally unique.state.json.daily_logs.entry_count as entry_count; it means the entry marker count in the latest active daily log, not a global cumulative count.validate_context.py; do not hand-edit managed markers, state.json, config.json, receipts, or helper-evidence stores.Use RecallLoom when you need to:
Typical triggers include:
On first explicit invocation in a project, RecallLoom should not assume the workspace is already initialized.
The correct flow is:
rl-init, run the standard initialization action3.10+, stop with a blocked runtime result instead of hand-building a sidecarrl-init SHOULD mean: initialize the sidecar, validate the workspace, and return next recommended actions. Treat it as a stable high-level action name even when the host does not expose native slash commands.
For the current package line, the stable operator-facing wrapper targets are:
rl-initrl-resumerl-statusrl-validaterl-init is the primary operator-friendly first-attach action name.
The others are operator-facing stable action names that can be interpreted by the host agent or mapped into native custom commands when the host supports that surface.
rl-bridge remains the canonical dispatcher/helper action label for bridge work, but this package line does not promise a universal native wrapper or deterministic first-hop routing for that label.
Natural language remains the default public phrasing for these actions.
The dispatcher command surface also includes quick-summary, record --suggest, record --plan, append, write, sync-current-state-after-append, and repair-daily-log-cursor.
For append, write, and sync-current-state-after-append only, use
--compact-json when a bounded transaction result is needed: it emits
recallloom.transaction.compact/1.0, remains below 2048 UTF-8 bytes, and is
mutually exclusive with the legacy schema-1.1 --json output.
Use quick-summary for current-state snapshots, record --suggest to produce a side-effect-free candidate recording prompt after a durable milestone/decision/validation signal, record --plan to classify a recording intent and get the next safe helper step, append --entry-json for milestone logging, write --type ... --source-file <prepared-file> --dry-run or write --type ... --stdin --dry-run before typed managed-file writes, and sync-current-state-after-append --reuse-current-summary --semantic-unchanged-assertion-json <json> only after preflight allows metadata-only post_append_summary_sync; see references/recording-workflow.md for the bound assertion JSON skeleton.
record --suggest never writes, never watches in the background, and never turns sensitive or attached raw material into a write path; it only returns a sanitized candidate summary and suggested record --plan path when a prompt is appropriate.
Use repair-daily-log-cursor in preview mode first when state.json.daily_logs no longer matches the parsed latest active daily log. Preview returns a public-safe repair classification, preview_digest, expected workspace revision, confirmation material, and post-repair validation step. Apply mode requires --apply --yes plus a fresh preview binding through --expected-workspace-revision or --preview-digest, is support-gated as mutating, and repairs cursor fields without writing helper receipts or rewriting daily-log content.
These dispatcher additions are optional for existing v0.3.4 projects and do not change sidecar protocol 1.0.
Native wrappers for rl-init, rl-resume, rl-status, and rl-validate
are convenience entrypoints only. They must delegate to the same dispatcher and
must not replace natural-language restore requests, bypass helpers, or create a
host-specific product logic copy.
When a host or agent sees a generic initialized-project restore request:
For the current package line, rl-resume is the single stable operator-facing action name for that initialized-project restore checkpoint.
Natural-language restore requests are still the primary public path.
Do not invent a manual sidecar fallback or a host-local restore alias that is not backed by the package contract.
RecallLoom should default to user task language, not implementation language.
coldstart label unless the user is explicitly doing operator/debug work.RecallLoom should treat fast path as the default interaction mode.
Resume mode selection:
resume or status when the next agent needs the normal tiered read-plan guidance before deciding what to read.resume --fast when current-state orientation is enough and the next safe move can be chosen from state.json plus rolling_summary.md.resume --full when stable framing, source-of-truth routing, or project-local update_protocol.md guidance is needed before action.query_continuity.py; fast and full resume modes should not expand into daily logs by default.RecallLoom uses three primary memory layers:
STORAGE_ROOT/context_brief.md: stable project framingSTORAGE_ROOT/rolling_summary.md: overwrite-style current-state snapshotSTORAGE_ROOT/daily_logs/YYYY-MM-DD.md: append-only milestone evidenceSTORAGE_ROOT/config.json: machine-readable workspace settingsSTORAGE_ROOT/state.json: machine-readable sidecar state for concurrency-aware helpersSTORAGE_ROOT/update_protocol.md: recommended project-local override layer for read and write behaviorFile responsibilities in one sentence:
context_brief.md explains what this project is and how it should be approached.rolling_summary.md explains what is true right now.daily_logs/ explain what happened at milestone level.config.json keeps storage and language settings stable.state.json tracks workspace revision and helper-visible sidecar state.update_protocol.md, when present, can narrow or strengthen the default read/write rules for this specific project.STORAGE_ROOT is either PROJECT_ROOT/.recallloom/ or PROJECT_ROOT/recallloom/. Exactly one valid storage root MAY exist; if both exist, stop instead of guessing.
Machine-readable markers, not heading labels, are the normative file contract. Protocol 1.0 supports workspace languages en and zh-CN. See references/file-contracts.md.
STORAGE_ROOT/config.json.STORAGE_ROOT/state.json.STORAGE_ROOT/rolling_summary.md.STORAGE_ROOT/update_protocol.md exists, surface it before expanding beyond the minimum continuity set.STORAGE_ROOT/context_brief.md only when the current task needs framing, scope, source-of-truth, or phase context that the summary does not already cover.Cold start should restore and judge first.
It should not automatically continue next_step or execute project work just because continuity files were read.
See references/operation-playbooks.md for the full flow.
Three read-side helpers matter here:
preflight_context_check.py: revision-aware freshness review before formal writes; returns handoff-first digests, suggested read targets, write-tier guidance, and trust/drift state.summarize_continuity_status.py: ambient continuity status surface on the same freshness baseline; returns the same digest family plus shared workday-state and trust/drift guidance.query_continuity.py: read-only continuity recall surface; returns answer-first recall with answer, supporting citations, and a risk/freshness note. It also returns hits, token estimate, budget hint, freshness/conflict state, trust/drift state, an output variant label, and override review targets. Daily-log citations include explicit date values, current-state files win ties, and the context window stays bounded.All attach-safe continuity text returned through these read-side surfaces is expected to respect the shared attached-text scan rules.
STORAGE_ROOT/update_protocol.md if it exists.current_state changes usually target rolling_summary.md.stable_rule changes usually target context_brief.md.milestone_evidence usually targets the daily log.Default exits before any write should stay explicit:
no_write is a normal successful resultmerge_current_state updates rolling_summary.mdappend_milestone appends to the daily logconfirm and blocked stop automatic writes rather than guessingRead-side trust notes:
sidecar_trust_state stays in helper JSON, not in protocol 1.0state.json.provenance may store local provenance markers such as structurally_valid, review_imported_baseline, or helper_evidenced after a receipt-finalized helper write; helper JSON still owns operational provenance_state routingstructurally_valid and review_imported_baseline mean structural/readiness evidence only and MUST NOT be treated as helper_evidencedhelper_evidencedrl-validate / validate_context.py remains structural and does not read the optional receipt store. Receipt-store validation is explicit: use --require-provenance with exactly one scope flag, --changed-only or --full.continuity_drift_risk_level is a review signal, not proof that the sidecar is damagedallowed_operation_level and write_readiness help hosts route low-risk read vs review-first vs write-after-preflight flowsProject-local overrides MAY narrow read order, write order, or archive behavior, but they do not replace the core file contract.
Before writing continuity content, the agent should make the layer decision itself. Helpers can provide safe write context and static write-tier guidance, but they must not replace agent judgment about what the content means.
Use this quick check before editing managed files:
no_write the right result?stable_rule, current_state, or milestone_evidence?multi_layer_split?defer or confirm rather than guess?Layer defaults:
stable_rule: long-lived workflow rules, source-of-truth routing, project boundaries, or recovery facts. Default target: context_brief.md.current_state: what is true now, including current phase, active risks, active judgments, and next steps. Default target: rolling_summary.md.milestone_evidence: completed validations, approvals, releases, accepted decisions, or other durable evidence. Default target: daily log.no_write, defer, and confirm are valid outcomes when nothing durable changed, the discussion is unstable, or the boundary needs explicit approval.When more than one layer is valid, split different facts across layers and do not duplicate the same sentence.
For the detailed rules, conflict order, self-review template, and anonymized calibration cases, see references/operation-playbooks.md.
For protocol 1.0, update_protocol.md is a human-reviewed override layer; helpers surface it but do not automatically execute its natural-language rules.
RecallLoom prefers the smallest valid write set. The agent decides what should change and prepares content; helpers decide whether the write is still safe to apply.
When generating workspace files, prefer the user's workspace language when it is supported by protocol 1.0 (en, zh-CN).
Do not update context files just because:
The protocol is designed to reduce noise, not to turn every session into documentation work.
RecallLoom provides four profiles:
profiles/general-project-continuity.mdprofiles/research-writing.mdprofiles/product-doc-collaboration.mdprofiles/software-project-coordination.mdProfiles refine emphasis, evidence handling, and drift risk. Use general-project-continuity.md by default; switch to a specialized profile only when the project shape is a high-confidence match.
RecallLoom does not try to be:
It is the project continuity layer, not the whole agent stack.
references/protocol.mdreferences/file-contracts.mdreferences/operation-playbooks.mdreferences/anti-patterns.mdreferences/profiles.mdThis package is released under Apache License 2.0.
© Frappucc1no, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 124 other files (scripts, references) in skills/recallloom of Frappucc1no/recall-loom.
Open the folder on GitHubat commit a103b6d
Recallloom next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Recallloom this skillFrappucc1no/recall-loom | 154 | — | ~6.3k | Automated safety check: Pass | Apache-2.0 | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Beads Task Memorygastownhall/beads | 28k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Reflect on Session Learningscursor/plugins | 11k | 5 repos | ~1.2k | Automated safety check: Pass | None | |
| MemPalace Memory SearchMemPalace/mempalace | 59k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Compound Learning WriterEveryInc/compound-engineering-plugin | 25k | — | ~2k | Automated safety check: Pass | MIT |
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
gastownhall/beads
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
cursor/plugins
Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.
MemPalace/mempalace
Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.
EveryInc/compound-engineering-plugin
Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.
slopus/happy
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
Categories
A skill your agent uses when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or recording meaningful…. Recallloom is an agent skill from Frappucc1no/recall-loom. Use when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or recording meaningful progress across sessions.
Recallloom fits situations like: A task involves continuing a project; restoring project context; maintaining file-based project memory; updating current-state summaries.
Run `npx skills add Frappucc1no/recall-loom --skill recallloom -a claude-code`. Or copy the skill folder (skills/recallloom in Frappucc1no/recall-loom) into .claude/skills/recallloom in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Frappucc1no/recall-loom --skill recallloom -a codex`. Or copy the skill folder (skills/recallloom in Frappucc1no/recall-loom) into .agents/skills/recallloom in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Frappucc1no/recall-loom --skill recallloom -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recallloom, .gemini/skills/recallloom, .github/skills/recallloom and .opencode/skills/recallloom in your project.
SKILL.md names no scripts, command-line tools or credentials: Recallloom is instructions for the agent only. Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Recallloom is published under the Apache-2.0 licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 6.3k tokens (SKILL.md is roughly 25k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 28k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Recallloom: Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), Beads Task Memory (gastownhall/beads, 28k stars), Reflect on Session Learnings (cursor/plugins, 11k stars) and MemPalace Memory Search (MemPalace/mempalace, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Frappucc1no (a GitHub user) maintains it in Frappucc1no/recall-loom, which has 154 GitHub stars. The repository was last updated on August 6, 2026.
Source: Frappucc1no/recall-loom on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.