Agent skill

Memory And Handoff

by romiluz13 in romiluz13/cc10x

Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable…

MITAuto-check: notesAgent Workflows

Install Memory And Handoff

skills CLI
$ npx skills add romiluz13/cc10x --skill memory-and-handoff -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install romiluz13/cc10x memory-and-handoff --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/romiluz13/cc10x.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/cc10x/skills/memory-and-handoff .claude/skills/memory-and-handoff && rm -rf skills-src

Use ~/.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/

Facts

Skill name
memory-and-handoff
GitHub stars
164
Token cost
~2.7k tokens
SKILL.md length
1,186 words
Files
5 (incl. references)
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable…

  • Works in 3 steps: Write to OS temp dir, never into the… → Reference artifacts by path/URL, never… → Redact secrets and PII before writing.…
  • Tasks that involve Agent memory
  • SKILL.md covers Reference Files, Mode: SESSION MEMORY, Mode: HANDOFF PACKAGE and Knowledge Compounding Loop
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Memory And Handoff is an agent skill from romiluz13/cc10x. Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/context-budget-and-checkpointing.md`, `references/memory-file-contracts.md` and `references/memory-model-and-ownership.md`).

It sits in Agent Workflows, covering Agent memory. It works with Git. The repository describes itself as: The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review. The licence is MIT.

When your agent uses it

  • Tasks that involve Agent memory

Example prompts

  • “/memory-and-handoff”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Grep, Glob

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Write to OS temp dir, never into the repo — a repo-committed handoff becomes a stale doc the next reader mistakes for current truth…
  2. Reference artifacts by path/URL, never paste contents. The next reader has the repo. They need a map, not a copy. Prefer behavioral…
  3. Redact secrets and PII before writing. Redact per ### Secret Redaction above.

What it can do on your machine

Read from SKILL.md and the folder at commit f346ebe. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Bash
    • Grep
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Memory And Handoff loads about 2.7k tokens when it runs, and up to ~5.1k if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 1,186 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.1k

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.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Bash, Grep, Glob

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from romiluz13/cc10x at commit f346ebe, republished under its MIT licence (© romiluz13). 1,186 words, ~2,707 tokens.

Download SKILL.mdSave it as .claude/skills/memory-and-handoff/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
memory-and-handoff
description
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.
allowed-tools
Read, Write, Edit, Bash, Grep, Glob
user-invocable
false

Memory & Handoff

Reference Files

Read only what's needed:

  • references/memory-model-and-ownership.md — memory surfaces, ownership, promotion, workflow markers; load when deciding which surface holds a piece of state or who may write it
  • references/memory-operations.md — permission-free operations, router-only persistence, edit patterns; load when actually reading or writing .cc10x/ files
  • references/memory-file-contracts.md — required headings, stable anchors, templates, auto-heal rules; load when creating a memory file or healing a malformed one
  • references/context-budget-and-checkpointing.md — context-budget rules, warning signs, checkpoint triggers; load when context is getting heavy or before a compaction/checkpoint decision

Mode: SESSION MEMORY

Memory is an index, not a transcript. Distill decisions, learnings, references, and verification evidence into durable, reusable notes.

Memory Surfaces
FileHolds
.cc10x/activeContext.mdcurrent focus, recent changes, decisions, learnings, references, blockers
.cc10x/patterns.mdreusable project standards, gotchas, conventions, skill hints
.cc10x/progress.mdcurrent workflow, tasks snapshot, completed items, verification evidence
.cc10x/workflows/{wf}.json + .events.jsonldurable orchestration truth (machine-owned, verbatim)
.cc10x/qa/QA route artifacts: {workflow_uuid}/feature-map.md, test-plan.md, env-plan.md, report.md, and per-environment env/{env_key}/setup.md (router- and QA-agent-owned)
.cc10x/state/git-approval.jsongit approval token written by the router and read by the git guard
docs/plans/*, docs/research/*detailed artifacts; memory points to them
Ownership
  • Router loads and auto-heals memory files before routing or resume
  • WRITE agents read memory but do NOT edit .cc10x/*.md (sole carve-out: bug-investigator's [DEBUG-N] lines)
  • WRITE agents emit structured MEMORY_NOTES in their Router Contract
  • READ-ONLY agents emit ### Memory Notes (For Workflow-Final Persistence)
  • Router-owned memory-finalize task is the only final writer of memory markdown files
  • Router-owned markers ([DEBUG-RESET: wf:{...}], [cc10x-internal] memory_task_id) are read and respected; agents do not invent replacements
Load (MANDATORY at workflow start)

Read all three: activeContext.md, patterns.md, progress.md.

Re-read before: architectural decisions (patterns.md + activeContext.md ## Decisions), implementation choices (patterns.md + activeContext.md), debugging (all three), planning next steps (progress.md + activeContext.md), claiming completion (progress.md + plan/design/research refs), user says "continue" (all three).

Persist

Emit MEMORY_NOTES in Router Contract:

yaml
MEMORY_NOTES:
  learnings: ["Key causal insight"]
  patterns: ["Reusable gotcha or convention"]
  verification: ["`npm test` -> exit 0"]
  deferred: ["Non-blocking follow-up or risk"]

Keep each entry one line — memory reloads every session; each extra line is a recurring tax. Prefer stable nouns over temporary wording. Put verification truth in verification, not prose. Put non-blocking work in deferred, not ad-hoc tasks.

Persist only memory-worthy items: decisions that change direction, learnings that prevent mistakes, verification evidence with commands and exit truth, deferred non-blocking issues, plan/design/research references, clarified user standards.

Do not persist: whole diffs, verbose logs, celebratory narration, "looked correct" without evidence, duplicate notes, raw secrets/PII in outward artifacts.

Secret Redaction (OUTWARD artifacts only)

Before router persists cc10x-authored content into outward artifacts (docs/plans/*, docs/research/*, design docs, persisted memory notes): redact pasted tokens, API keys, connection-strings, credentials, PII. Replace with <redacted:secret> (PII: <redacted:pii>). Keep surrounding constraint intact. When unsure, redact. Does NOT apply to internal machine-owned .cc10x/ orchestration state — that stays verbatim for resume/dedupe keys.

Compaction KEEP / SUMMARIZE / DROP Rubric
TierWhatRule
KEEPuser hard-constraints/prohibitions, exact next step, open failures + errorspreserve VERBATIM — never paraphrase a constraint or error
SUMMARIZEresolved decisions with rationale, concluded attempts, discovered file/module boundariesdistill to one durable line each
DROPdecorative prose, step-by-step diary, superseded speculation, redundant prompt retellingsdiscard

Persist user PROHIBITIONS verbatim into workflow artifact's intent field as soon as stated — compaction may fire before router's normal persist.

Project Skill Hints

After loading memory, check patterns.md ## Project SKILL_HINTS. Invoke listed skills when relevant and installed. Treat missing skills as non-fatal. Do not invent skill IDs. Do not edit ## Project SKILL_HINTS directly — surface recommendations in planner output or memory notes.


Mode: HANDOFF PACKAGE

A portable, human-readable export for when the next reader is NOT this cc10x session — a coworker, a different tool, or a clean session with no cc10x router.

cc10x's own resume is structural (.cc10x/ + router rehydrates). The handoff package is the bridge OUT to a reader who cannot read .cc10x/ orchestration state.

Rules
  1. Write to OS temp dir, never into the repo — a repo-committed handoff becomes a stale doc the next reader mistakes for current truth. HANDOFF="${TMPDIR:-/tmp}/handoff-$(date +%Y%m%d-%H%M%S).md". Print the absolute path.
  2. Reference artifacts by path/URL, never paste contents. The next reader has the repo. They need a map, not a copy. Prefer behavioral descriptions over file:line where code may still drift.
  3. Redact secrets and PII before writing. Redact per ### Secret Redaction above.
Show full SKILL.md (515 more words)Show less
Contents
SectionHolds
Goalone-line objective, verbatim user intent if stated
Current statewhere things stand, one short paragraph
What's donereference artifacts by path; do not re-narrate
What's nextEXACT next step — concrete enough to start cold
Open blockers / failuresunresolved errors VERBATIM, failing commands, dead ends tried
Suggested skills / toolswhich skills the next agent should invoke to continue
Artifacts (by path)plan, diff/PR, key source files with behavioral descriptions

The "suggested skills/tools" pointer is load-bearing: tell the next agent how to continue. If cc10x is present: invoke cc10x-router. If not: name domain skills and point at plan/research docs.


Knowledge Compounding Loop

Memory is not just for context survival — it's for system self-improvement. After every BUILD or DEBUG cycle, structured learnings should compound into reusable knowledge. Memory files (activeContext.md, patterns.md, progress.md) hold session-scoped context; durable, structured learnings that survive across projects and sessions go to docs/solutions/.

What the router implements today. Capture (step 1) and the solution-doc threshold in ### When to Write a Solution Doc: the router's memory task persists the learnings and applies those three conditions at workflow finalize. Grounding (step 2) is partial: cc10x:debugging and cc10x:planning check docs/solutions/ when it exists, and no session-start loader reads it. Deferred, not implemented by the router: consolidate-at-3+ on patterns.md (step 3), the periodic refresh with the five-outcome model (step 4; the ### Compounding Outcomes table is guidance for a person or agent doing that review), and the CLAUDE.md/AGENTS.md discover step (step 5).

The Loop
  1. Capture — During workflow-finalize, the router writes structured learnings from agent MEMORY_NOTES into activeContext.md ## Learnings and patterns.md ## Common Gotchas; learnings that cross the solution-doc threshold (below) are written to docs/solutions/.
  2. Ground — Before starting new work, agents read patterns.md, activeContext.md, and docs/solutions/ to avoid repeating solved problems.
  3. Consolidate — When the same gotcha appears 3+ times in patterns.md, promote it to a solution doc under docs/solutions/.
  4. Refresh — Periodically audit learnings and solution docs with the five-outcome model (below).
  5. Discover — Ensure CLAUDE.md or AGENTS.md points to docs/solutions/ so agents can find it.
When to Write a Solution Doc

After any non-trivial debug or build cycle, the router (during memory-finalize) evaluates whether to write a solution doc:

  • Write if: the problem took 3+ hypotheses (debug attempts) to solve, OR the same defect pattern appears in 3+ files, OR the solution contradicts a documented assumption in patterns.md
  • Skip if: the fix was mechanical (typo, import error, one-line change)
  • Offer neutrally if: the lesson is one sentence (mention in memory notes instead)
Compounding Outcomes

When reviewing prior learnings during memory-finalize (or auditing solution docs), apply one of five outcomes:

OutcomeWhenAction
KeepLearning is still accurate and usefulLeave as-is
UpdateLearning is correct but incompleteAdd the missing detail
ConsolidateSame lesson appears multiple timesMerge into one entry, remove duplicates
ReplaceLearning is outdated or supersededReplace with the current truth
DeleteLearning no longer applies (framework changed, code removed)Remove it

Why this matters: Without consolidation, memory accumulates stale entries that mislead future work. The compounding loop ensures memory gets sharper over time, not just larger.

Solution Doc Format
markdown
# [Problem Title]
Category: [debugging | architecture | testing | workflow | conventions]
Tags: [comma-separated]
Date: YYYY-MM-DD

## Problem
[What went wrong — symptoms, not just the error message]

## What Didn't Work
[Hypotheses that failed and why]

## Solution
[What actually worked — with code example if applicable]

## Why
[Why the solution works — the underlying principle]

## Prevention
[How to prevent this class of problem in the future]

© romiluz13, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in plugins/cc10x/skills/memory-and-handoff of romiluz13/cc10x.

  • SKILL.md
  • references/context-budget-and-checkpointing.md
  • references/memory-file-contracts.md
  • references/memory-model-and-ownership.md
  • references/memory-operations.md

Open the folder on GitHubat commit f346ebe

Compare with similar skills

Memory And Handoff 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.

Memory And Handoff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memory And Handoff this skillromiluz13/cc10x164—~2.7kAutomated safety check: NotesMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Beads Task Memorygastownhall/beads28k—~1.2kAutomated safety check: PassMIT
Session History Searchslopus/happy24k—~3.1kAutomated safety check: PassMIT
Ownmemgrpcer/ownmem423—~593Automated safety check: PassApache-2.0
Watchmen Setupfirstbatchxyz/watchmen296—~1.1kAutomated safety check: NotesMIT

Similar skills

  • 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.

    21k GitHub stars~1.9k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed
  • Beads Task Memory

    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.

    28k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • 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.

    24k GitHub stars~3.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Ownmem

    grpcer/ownmem

    Recall this repository's OwnMem local memory before changing code, and keep it healthy.

    423 GitHub stars~593 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Watchmen Setup

    firstbatchxyz/watchmen

    Walks through installing watchmen, running its init wizard, wiring the plugin into Codex or Claude Code and checking the result with doctor.

    296 GitHub stars~1.1k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check: notes
  • AI Project Memory

    tudoumashu/ai-memory-skillpack

    Maintain bounded, durable AI project memory in a repository's docs/ai/ pack.

    422 GitHub stars~1.1k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

More from romiluz13/cc10x

All 22 skills in this repo
  • Building

    romiluz13/cc10x

    A skill your agent uses when writing production code test-first: the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation…

    164 GitHub stars~2.7k tokensUpdated yesterday
    Auto-check: notes
  • Diff Driven Docs

    romiluz13/cc10x

    A skill your agent uses when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation.

    164 GitHub stars~2.7k tokensUpdated yesterday
    Auto-check: notes
  • Planning

    romiluz13/cc10x

    A skill your agent uses when writing an execution plan or a decision RFC: task decomposition, context references, validation levels, risk-based testing, ADR format, plan completeness gate, and…

    164 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Verification

    romiluz13/cc10x

    A skill your agent uses when judging whether a task reached its goal, not just finished: the gate function, self-critique gate, validation levels, evidence array protocol, and goal-backward lens.

    164 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check: notes
  • Agent Common

    romiluz13/cc10x

    A skill your agent uses when a cc10x agent starts a task: the shared preamble for the memory protocol, the contract format, and the output rules.

    164 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Cc10x Guide

    romiluz13/cc10x

    Answers questions about cc10x itself — what it is, how to install and configure it, how the router, workflows, memory, and hooks operate, and how to troubleshoot.

    164 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Memory And Handoff

What does Memory And Handoff do?

Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable…. Memory And Handoff is an agent skill from romiluz13/cc10x.cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.

When should I use Memory And Handoff?

Memory And Handoff fits situations like: tasks that involve Agent memory.

How do I install Memory And Handoff in Claude Code?

Run `npx skills add romiluz13/cc10x --skill memory-and-handoff -a claude-code`. Or copy the skill folder (plugins/cc10x/skills/memory-and-handoff in romiluz13/cc10x) into .claude/skills/memory-and-handoff in your project. Claude Code loads it when a task matches its description.

How do I install Memory And Handoff in Codex?

Run `npx skills add romiluz13/cc10x --skill memory-and-handoff -a codex`. Or copy the skill folder (plugins/cc10x/skills/memory-and-handoff in romiluz13/cc10x) into .agents/skills/memory-and-handoff in your project. Codex loads it when a task matches its description.

Can I use Memory And Handoff in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add romiluz13/cc10x --skill memory-and-handoff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory-and-handoff, .gemini/skills/memory-and-handoff, .github/skills/memory-and-handoff and .opencode/skills/memory-and-handoff in your project.

What does Memory And Handoff need to run?

SKILL.md names no scripts, command-line tools or credentials: Memory And Handoff is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Grep, Glob.

Does Memory And Handoff access the network?

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.

Is Memory And Handoff safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Memory And Handoff use?

Memory And Handoff is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Memory And Handoff use?

About 2.7k tokens (SKILL.md is roughly 11k 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 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Memory And Handoff?

Skills that share tags, products or a category with Memory And Handoff: Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), Beads Task Memory (gastownhall/beads, 28k stars), Session History Search (slopus/happy, 24k stars) and Ownmem (grpcer/ownmem, 423 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memory And Handoff?

romiluz13 (a GitHub user) maintains it in romiluz13/cc10x, which has 164 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 7, 2026.

Source: romiluz13/cc10x on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.