Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/fo0/clawstash/donenpx skills add fo0/clawstash --skill donegit clone --depth 1 https://github.com/fo0/clawstashWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00067 | $0.01337 |
| Opus 5 | $0.00034 | $0.00668 |
| Sonnet 5 | $0.00013 | $0.00267 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
done scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Done — Work Closure
When to Use
- User says "done", "fertig", "finished", "abschluss", "/done"
- End of a feature, bugfix, or task when ready to wrap up
Workflow
1. Detect branch context
git rev-parse --abbrev-ref HEAD && git status --porcelain && git log origin/$(git rev-parse --abbrev-ref HEAD)..HEAD --oneline 2>/dev/null || echo "no upstream"
Classify:
main/master/develop/trunk-> main branch mode (conservative)- anything else -> feature branch mode (standard)
2. Read CLAUDE.md closure requirements
- Commands section -> identify format / lint / typecheck / test / build commands
- Git Conventions -> commit format (Conventional Commits), branch rules, merge strategy
- Documentation Rules -> verify affected docs (CLAUDE.md, README.md, MEMORY.md, SCRATCHPAD.md, BACKLOG.md) are up to date
3. Auto-format (write mode)
Run the project's format-write command from CLAUDE.md Commands block (npm run format -> prettier --write .). This MUST run before lint/typecheck/test/build -- formatting drift introduced during the session otherwise reaches CI and fails format:check.
- If no format-write command is listed in CLAUDE.md, skip this step (project has no formatter configured).
- If formatting changed files, stage them with
git add -uso they go into the upcoming commit (step 6) -- do NOT split formatting into its own commit. - Re-run
git status --porcelainafter formatting to see what changed.
4. Run automated checks
Execute the project's lint/typecheck/test/build commands from CLAUDE.md. If any fail:
- Feature branch: report failure, stop. Do not commit.
- Main branch: hard stop. Never push to main on red.
5. Verify scope + GitNexus read-only guard
If GitNexus is available, confirm the change scope (read-only):
gitnexus_detect_changes({scope: "all"})
Surface any unexpected affected processes. Then run git status and verify no unexpected .claude/**, CLAUDE.md, AGENTS.md, or agent_docs/** changes are staged -- if GitNexus (or anything else) touched them and they weren't the point of the task, revert with git checkout -- <paths> before committing.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 109 lines · 67 tokens per session scan A 8dd97b28221f
done is a skill published in the GitHub repository fo0/clawstash (1 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,337 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-telemetry
Catalog of OpenTelemetry instrumentation built into framework @cyanheads/mcp-ts-core — spans, metrics, completion logs, env config, runtime caveats, custom instrumentation patterns, and cardinality rules. Use when enabling OTel export, adding custom spans or metrics in services, debugging missing telemetry, looking up…
maintenance
Investigate, adopt, and verify dependency updates — with special handling for @cyanheads/mcp-ts-core. Captures what changed, understands why, cross-references against the codebase, adopts framework improvements, syncs project skills, and runs final checks. Supports two entry modes: run the full flow end-to-end, or…
add-test
Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.
polish-docs-meta
Finalize documentation and project metadata for a ship-ready MCP server. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.