Agent skill

Spectre Work Record

by joenandez in joenandez/spectre

Record bounded history at owned Execute, Ship, standalone Create PR, blocked-handoff, snapshot or correction boundaries.

MITAuto-check passedDevelopment

Install Spectre Work Record

skills CLI
$ npx skills add joenandez/spectre --skill spectre-work-record -a claude-code

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

GitHub CLI
$ gh skill install joenandez/spectre spectre-work-record --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/joenandez/spectre.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/spectre/skills/spectre-work-record .claude/skills/spectre-work-record && 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
spectre-work-record
GitHub stars
164
Token cost
~1.4k tokens
SKILL.md length
546 words
Files
2 (incl. references)
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

Record bounded history at owned Execute, Ship, standalone Create PR, blocked-handoff, snapshot or correction boundaries.

  • Works in 7 steps: One record per exact Execute run: resume… → Execute start requires exact… → New/current-run writes read git… → …
  • Tasks that involve Pull requests
  • SKILL.md covers Purpose, Inputs, Working Set and Outputs + DONE, plus 3 more sections
  • Calls git and gh

What it does

Spectre Work Record is an agent skill from joenandez/spectre. Record bounded history at owned Execute, Ship, standalone Create PR, blocked-handoff, snapshot or correction boundaries. Requires exact ownership. Not for reusable guidance, routine progress, batches or orchestrated Create PR.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/work-capture-input.json`).

It sits in Development, covering Pull requests. The repository describes itself as: Spectre is a battle-tested 6 stage agentic engineering workflow for building complex, production-ready features. You stay in the loop for the decisions that matter. Your agents…. The licence is MIT.

When your agent uses it

  • Tasks that involve Pull requests

Example prompts

  • “/spectre-work-record”

Workflow steps

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

  1. One record per exact Execute run: resume revises it; distinct runs never fold regardless of branch/feature/candidate. Branches/PRs may…
  2. Execute start requires exact identity/branch; every not-yet-true section says None yet., not placeholders (TODO, REPLACE_ME, angle…
  3. New/current-run writes read git rev-parse --abbrev-ref HEAD, require explicit exact branch evidence, compare independent run-start…
  4. Existing PR identity/URL requires gh pr view --json state outside store locks. Pass observed pullRequest; unavailable/unknown state…
  5. Authorized terminal Execute uses execution.state: finalized, remainingWork: "None." exactly (otherwise CAPTURE_INPUT_INVALID)…
  6. Fill semantic JSON outside the store; submit on stdin
  7. At owned terminal boundaries, promote only qualified reusable discoveries absent from maintained guidance via /spectre:spectre-capture, or…

What it can do on your machine

Read from SKILL.md and the folder at commit 931c9e8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use git and gh, which can reach the network depending on how they are called.

    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

Spectre Work Record loads about 1.4k tokens when it runs, and up to ~1.7k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 546 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.7k

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 passed

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from joenandez/spectre at commit 931c9e8, republished under its MIT licence (© joenandez). 546 words, ~1,367 tokens.

Download SKILL.mdSave it as .claude/skills/spectre-work-record/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
spectre-work-record
description
Record bounded history at owned Execute, Ship, standalone Create PR, blocked-handoff, snapshot or correction boundaries. Requires exact ownership. Not for reusable guidance, routine progress, batches or orchestrated Create PR.
user-invocable
false

work-record

Purpose

Truthful work history; workflow state/telemetry own live progress. Capture never changes delivery, verification or acceptance authority.

Inputs

  • Exact run/work identity and applicable branch, PR or repository/base/head/diff association; observed lifecycle, account, entry points, tag intent and prior revision.
  • Owned boundary: one Execute start/completion; meaningful blocked handoff/resolution when authority, control or context prevents safe continuation/resumption; Ship after PR creation; standalone Create PR terminal write only without an Execute/Ship owner; explicit snapshot/correction, including outside workflows.

Working Set

  • Reuse applicable discoveries/loads; refine only unresolved questions. Read references/work-capture-input.json and ${CLAUDE_PLUGIN_ROOT}/skills/spectre-capture/references/tagging-policy.md.
  • Use acquired entry points; focus-read as needed: path, symbol/document section, observed positive line, role. Explain unavailable/non-code portions, including uncreated start locations; never invent locations or dump files.

Outputs + DONE

Short title/routing summary and required identity/provenance/status metadata, derived reliably. Complementary fields:

  • requestedOutcome: request; scope: boundaries.
  • actualChanges: delivered behavior/artifacts; reasons: non-obvious rationale/trade-offs. Start/blocked accounts distinguish delivered from undelivered.
  • discoveries: findings and maintained-authority links; relatedContext: typed entry points and bounded references.
  • verification: observed checks; remainingWork: residual implementation. Structured verification and PR lifecycle remain authoritative.

State absence truthfully; omit filler, duplicated narrative/state. New/revised accounts stay under 2,000 estimated rendered tokens; reference evidence, not logs.

DONE: permitted boundary has a truthful account or surfaced skip/no-op/conflict/failure, with exact work ID, revision and canonical recordPath when applicable.

Method / guardrails

  1. One record per exact Execute run: resume revises it; distinct runs never fold regardless of branch/feature/candidate. Branches/PRs may reference multiple records. Execute-owned writes include --source-run-id <exact-run> alongside other identity flags for receipt derivation.
  2. Execute start requires exact identity/branch; every not-yet-true section says None yet., not placeholders (TODO, REPLACE_ME, angle brackets). Capture only the Inputs boundaries, never tasks, batches, checks, reviews, commits, ordinary decisions, routine progress, transient remediation or context refreshes.
  3. New/current-run writes read git rev-parse --abbrev-ref HEAD, require explicit exact branch evidence, compare independent run-start evidence when available and preserve known same-run branch. Return recovery/skip if unavailable. Exact historical corrections may preserve unknown original branch by omitting --branch; never backfill from today's checkout. New historical snapshots require verified original branch.
  4. Existing PR identity/URL requires gh pr view <identity-or-url> --json state outside store locks. Pass observed pullRequest; unavailable/unknown state, terminal-history contradiction or unqueryable draft without identity returns recovery/skip. Execution, verification and PR states stay separate:
    • execution: unknown|in-progress|implementation-ready|acceptance-pending|blocked|finalized.
    • verificationState: unknown|not-run|checked|passed|failed.
    • pullRequest: unknown|none|draft-open|closed|merged; bare open is invalid.
  5. Authorized terminal Execute uses execution.state: finalized, remainingWork: "None." exactly (otherwise CAPTURE_INPUT_INVALID). Blocked/failed/interrupted accounts stay non-final with scoped residual work; review, CI, PR readiness, merge and closure are not implementation work.
  6. Fill semantic JSON outside the store; submit on stdin: knowledge-cli.mjs capture --kind work --input - --project-dir <project-dir> --json. New/current-run writes add --branch <exact-branch> and exact identity via --work-id <id>, --source-run-id <run>, --pull-request-id <pr> or --candidate <exact-json>. Historical corrections require --work-id <id> --expected-revision <revision>. Changed records require loaded revisionToken as --expected-revision and preserve omitted tags; unchanged retries are no-ops. --input <path> is only for explicit manual/advanced capture or returned recoveryInput.
  7. At owned terminal boundaries, promote only qualified reusable discoveries absent from maintained guidance via /spectre:spectre-capture, or link existing authority. No mandatory knowledge record per completion or added scan/write boundary. Capture failure/conflict returns recovery input without blocking delivery.
Show full SKILL.md (31 more words)Show less

Handoff

Boundary, exact work ID, revision/conflict, canonical recordPath, associations, lifecycle facts and applicable recovery input.

Escalate-If

Unclear ownership/boundary, conflicting historical authority or unrecoverable write: surface recovery/skip without guessing or blocking delivery.

© joenandez, 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 1 other file (references) in plugins/spectre/skills/spectre-work-record of joenandez/spectre.

  • SKILL.md
  • references/work-capture-input.json

Open the folder on GitHubat commit 931c9e8

Compare with similar skills

Spectre Work Record 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.

Spectre Work Record compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Spectre Work Record this skilljoenandez/spectre164—~1.4kAutomated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
PR Design DocOpenHands/OpenHands90k—~2.4kAutomated safety check: PassMIT
WooCommerce Code Reviewwoocommerce/woocommerce11k3 repos~1.1kAutomated safety check: PassCustom licence

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • PR Design Doc

    OpenHands/OpenHands

    For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…

    90k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Record PR Demo

    payloadcms/payload

    A skill your agent uses when a Payload pull request needs a concise visual walkthrough for reviewers.

    45k GitHub stars~1k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from joenandez/spectre

All 26 skills in this repo
  • Verify Spectre

    joenandez/spectre

    A skill your agent uses when validating that the Spectre plugin itself still works after ANY change to this repo — skills, prompts, agents, hooks, the CLI, the Codex mirror, or a release.

    164 GitHub stars~1.5k tokensUpdated 8 days ago
    Auto-check passed
  • A skill your agent uses when modifying the Codex SPECTRE install flow, SessionStart continuity, project skill syncing, registry injection, or Codex-specific runtime files.

    164 GitHub stars~2.2k tokensUpdated 8 days ago
    Auto-check passed
  • Spectre Handoff

    joenandez/spectre

    Save a quiet, branch-keyed session snapshot with continuity, active work, and optional task/todo state for automatic resume.

    164 GitHub stars~1.3k tokensUpdated 8 days ago
    Auto-check passed
  • Spectre Learn

    joenandez/spectre

    User-invoked front door for durable capture. An agent skill from joenandez/spectre.

    164 GitHub stars~1k tokensUpdated 8 days ago
    Auto-check passed
  • Spectre Rewrite Skill

    joenandez/spectre

    Rewrite a verbose SPECTRE skill into a compact, contract-form Spectre skill proposal — clear on WHAT, silent on HOW — grounded in the spectre-light distillation and freedom-tier budget.

    164 GitHub stars~3k tokensUpdated 8 days ago
    Auto-check passed
  • Spectre Rewrite Subagent

    joenandez/spectre

    Rewrite Spectre subagent definitions into compact, contract-driven agents with clear routing, least-privilege tools, output schemas, and an auditable rewrite trail.

    164 GitHub stars~1.8k tokensUpdated 8 days ago
    Auto-check passed

Categories

Questions about Spectre Work Record

What does Spectre Work Record do?

Record bounded history at owned Execute, Ship, standalone Create PR, blocked-handoff, snapshot or correction boundaries. Spectre Work Record is an agent skill from joenandez/spectre. Record bounded history at owned Execute, Ship, standalone Create PR, blocked-handoff, snapshot or correction boundaries.

When should I use Spectre Work Record?

Spectre Work Record fits situations like: tasks that involve Pull requests.

How do I install Spectre Work Record in Claude Code?

Run `npx skills add joenandez/spectre --skill spectre-work-record -a claude-code`. Or copy the skill folder (plugins/spectre/skills/spectre-work-record in joenandez/spectre) into .claude/skills/spectre-work-record in your project. Claude Code loads it when a task matches its description.

How do I install Spectre Work Record in Codex?

Run `npx skills add joenandez/spectre --skill spectre-work-record -a codex`. Or copy the skill folder (plugins/spectre/skills/spectre-work-record in joenandez/spectre) into .agents/skills/spectre-work-record in your project. Codex loads it when a task matches its description.

Can I use Spectre Work Record 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 joenandez/spectre --skill spectre-work-record -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spectre-work-record, .gemini/skills/spectre-work-record, .github/skills/spectre-work-record and .opencode/skills/spectre-work-record in your project.

What does Spectre Work Record need to run?

Going by SKILL.md and its folder, Spectre Work Record needs the command-line tools its instructions call (git and gh).

Does Spectre Work Record access the network?

SKILL.md contains no URLs. Its commands use git and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Spectre Work Record safe to install?

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. Review the folder before installing.

What licence does Spectre Work Record use?

Spectre Work Record 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 Spectre Work Record use?

About 1.4k tokens (SKILL.md is roughly 5.5k 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 376 tokens, read only when the agent opens those files.

What are the alternatives to Spectre Work Record?

Skills that share tags, products or a category with Spectre Work Record: Finishing a Development Branch (obra/superpowers, 297k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars) and PR Design Doc (OpenHands/OpenHands, 90k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Spectre Work Record?

joenandez (a GitHub user) maintains it in joenandez/spectre, which has 164 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 2, 2026.

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