Borrowing it
Nothing to install: this file belongs to chainofdive/ravenclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chainofdive/ravenclaw/main/.claude/skills/ravenclaw-context/SKILL.mdgit clone --depth 1 https://github.com/chainofdive/ravenclawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chainofdive/ravenclaw/ravenclaw-context)<a href="https://agentmods.dev/skills/chainofdive/ravenclaw/ravenclaw-context"><img src="https://agentmods.dev/badge/skills/chainofdive/ravenclaw/ravenclaw-context/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chainofdive/ravenclaw/ravenclaw-context"><img src="https://agentmods.dev/badge/skills/chainofdive/ravenclaw/ravenclaw-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00033 | $0.00458 |
| Opus 5 | $0.00016 | $0.00229 |
| Sonnet 5 | $0.00007 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
ravenclaw-context 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 9d ago.
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.
What it actually says
This skill helps you quickly load and apply work context from the Ravenclaw system.
Steps
1. Load Work Context
First, get the full work context. If the Ravenclaw MCP server is available, use the get_work_context tool. Otherwise, run the CLI:
rc context
2. Review Active Work
Check what's currently in progress:
rc issue list --status=in_progress --format=table
Check what's blocked or ready to start:
rc issue list --status=todo --format=table
3. Check User Comments
If working on a specific issue, check for user comments/feedback:
rc comment list issue <issue-id>
4. Start Working
Pick an issue to work on and mark it:
rc issue start <key>
5. When Done
Update the issue and add any relevant wiki documentation:
rc issue done <key>
rc wiki write <topic-slug>
6. Epic Locks (Multi-Agent Safety)
Before starting work on an epic's issues, acquire a lock:
rc lock acquire <epic-id> --session $SESSION_ID --agent claude-code
Keep the lock alive during long work:
rc lock heartbeat <epic-id> --session $SESSION_ID
Release when done:
rc lock release <epic-id> --session $SESSION_ID
Or simply use rc issue start <key> — it auto-acquires the epic lock.
Check for existing locks:
rc lock list
Tips
- Use
rc context --compactfor a token-efficient summary - Use
rc search "keyword"to find relevant epics, issues, or wiki pages - Always read comments before starting — the user may have specific instructions
- Update the wiki with architectural decisions or important context for future agents
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.
- 9d ago First seen · 82 lines · 33 tokens per session scan A 0052880e0dc4
ravenclaw-context is a skill published in the GitHub repository chainofdive/ravenclaw (13 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 458 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
lov-gh-tidy
Interactive GitHub repo hygiene skill. Lists all open issues, PRs, stale branches, and orphan labels, shows a summary of each with analysis, then asks the user how to handle each item (close, merge, comment, delete, keep). Executes all chosen actions via gh CLI. Use when the user says "清理 GitHub", "tidy repo", "clean…
multica-goal-tracker
Track goal-driven Multica issues. Use when a user creates or maintains Multica issues by pasting a /goal prompt, wants Codex to summarize that goal into a concise issue purpose, append a normalized goal-start comment, record completion evidence from real Multica execution run messages or a supplied session transcript…
handoff
Use when work is changing sessions, agents, or machines and the next pass needs a compact handoff document with current state, open questions, and next steps instead of raw chat history.
mastermind-project-history
Retrieve and reason from durable project decisions, failed approaches, audits, reports, and lessons without treating provenance, search rank, or user approval as technical proof. Use when asking why a design exists, whether an approach was tried, what supersedes an older decision, what prior evidence should constrain…