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/auerbachb/claude-code-config/recapnpx skills add auerbachb/claude-code-config --skill recapgit clone --depth 1 https://github.com/auerbachb/claude-code-configWhat 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 | $0.00042 | $0.04141 |
| Opus 5 | $0.00021 | $0.02070 |
| Sonnet 5 | $0.00008 | $0.00828 |
| Haiku 4.5 | $0.00004 | $0.00414 |
Grade A, and why
recap 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce a functional-improvement summary of a PR or issue: what the work did (a merged/open PR) or hopes to do (an open issue), written for a technical collaborator who wants the feature perspective — not the implementation walkthrough.
/recap is the single-target companion to /standup. /standup rolls up all recent activity across a time window for a daily report; /recap zooms in on one PR or issue and renders its functional story as nested bullets (or a table). Reach for /standup for "what happened lately"; reach for /recap for "explain this one PR/issue to my collaborator."
Output modes
| Mode | Flag | Effect |
|---|---|---|
| Nested bullets | (default) | Top-level bullet = functional change; sub-bullets = scope/notes |
| Table | --table |
Markdown table with Change | Notes columns |
| Full | --full |
Relax the word budget; keep nested-bullet (or table) structure |
| Technical | --technical |
Add a second tier of detail per bullet (mechanism, files, key endpoints) without removing the conversational top-level bullet |
Flags compose: --table --technical adds a third "Technical detail" column; --full --technical keeps both expansions.
Step 1: Parse arguments and flags
Parse $ARGUMENTS. Extract flags first, then interpret whatever remains as the target identifier.
- Flags (any order, anywhere in
$ARGUMENTS):--table,--full,--technical. Set a boolean for each; strip them from the argument string. - Target identifier — take the first non-flag token only (see batch handling below). It is one of:
- URL (
https://github.com/<owner>/<repo>/pull/123or.../issues/123) → extract both the<owner>/<repo>and the trailing number; the path segment (/pull/vs/issues/) fixes the type. The owner/repo from the URL must qualify every laterghcall (--repo <owner>/<repo>) — otherwise a URL for another repo would silently recap whatever item shares that number in the current repo. #Nor bare number (452,#457) → strip any leading#; target the current repo; type is not yet known (resolve in Step 2).- Empty → auto-detect (see below).
- URL (
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.
- 2d ago First seen · 256 lines · 42 tokens per session scan A 58d11751f22a
recap is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 4,141 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 2026-08-31.
Other skills, from other repositories
recon
Codebase reconnaissance agent for Bug Hunter. Maps architecture, identifies trust boundaries, classifies files by risk priority, and detects service boundaries. Does NOT find bugs — finds where bugs hide.
referee
Final arbiter for Bug Hunter. Receives Hunter findings and Skeptic challenges, independently re-reads code, and delivers authoritative verdicts with CVSS scoring and proof-of-concept generation for security findings.
bughunt
Performs an exhaustive 14-dimension bug hunt across the codebase using Draft context (architecture, tech-stack, product) for false-positive elimination. Generates a severity-ranked report with code evidence, data flow traces, and suggested fixes. Optionally writes regression tests. Use when the user asks to find bugs…
juror-review
Inspect Juror Cloud PR findings and, only after an explicit confirmation, start or rerun a hosted Juror review.
coverage
Compute code coverage for active track or module. Targets 95%+ coverage with report and justification for uncovered lines. Complements TDD workflow.
tech-debt
Identify, categorize, and prioritize technical debt across seven dimensions. Generates remediation plans with effort estimates. Offered by /draft:new-track for refactor tracks.