Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/stevesolun/ctxnpx agentmods add skills/stevesolun/ctx/repo-stats-autoupdateWrote 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/stevesolun/ctx/repo-stats-autoupdate)<a href="https://agentmods.dev/skills/stevesolun/ctx/repo-stats-autoupdate"><img src="https://agentmods.dev/badge/skills/stevesolun/ctx/repo-stats-autoupdate/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/stevesolun/ctx/repo-stats-autoupdate"><img src="https://agentmods.dev/badge/skills/stevesolun/ctx/repo-stats-autoupdate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.00728 |
| Opus 5 | $0.00033 | $0.00364 |
| Sonnet 5 | $0.00013 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
repo-stats-autoupdate 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-stats-autoupdate
What this skill does
Reads the authoritative sources for the ctx repo's key numbers and patches README.md in place so badges and inline counts never drift:
| Number | Source of truth |
|---|---|
| Skills | ~/.claude/skill-wiki/graphify-out/graph.json — count nodes where type == "skill" |
| Agents | same file — count nodes where type == "agent" |
| Graph nodes | len(graph["nodes"]) |
| Graph edges | len(graph["edges"]), formatted as 642K / 1.2M |
| Communities | graph/communities.json → total_communities |
| Converted pipelines | ~/.claude/skill-wiki/converted/ subdir count |
| Tests | checked-in README/docs inventory by default; set CTX_UPDATE_REPO_STATS_LIVE_TESTS=1 to refresh from pytest --collect-only -q |
Fields that can't be resolved (e.g. wiki not deployed) are left untouched — the updater never blocks a commit.
How to use it
One-time install (per clone):
git config core.hooksPath .githooks
After that, every git commit runs .githooks/pre-commit which calls the updater and re-stages README.md if any number drifted.
Manual run:
python src/update_repo_stats.py # patch README
python src/update_repo_stats.py --check # exit 1 if stale (for CI)
CTX_UPDATE_REPO_STATS_LIVE_TESTS=1 python src/update_repo_stats.py # refresh test inventory
When NOT to use it
- When you've deliberately phrased a number descriptively (e.g. "over 1,700 skills") — the regex patterns only match exact digits, so prose phrasings are safe, but double-check after big imports.
- When the wiki isn't deployed locally. The updater degrades gracefully: it prints a warning and skips fields it can't resolve. It does not invent numbers.
Known gaps (intentionally out of scope)
- Does not rebuild the graph or wiki. Rebuilding
graph/wiki-graph.tar.gztakes minutes and churns a large artifact — too heavy for per-commit. Runctx-wiki-graphify, thenpython src/validate_graph_artifacts.py --deep, and repack the tarball manually when the skill catalog changes materially. - Does not verify graph integrity. If
graphify-out/graph.jsonis corrupt, you'll get junk numbers. Run the wiki health check (python src/wiki_orchestrator.py --check) separately.
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 · 58 lines · 66 tokens per session scan A 66e37f6ef4b8
repo-stats-autoupdate is a skill published in the GitHub repository stevesolun/ctx (585 stars, last pushed 12d ago), licensed MIT. It adds 66 tokens to every session and 728 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 2026-09-03.
Other skills, from other repositories
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.
core-workflow
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, testing strategy, and communication standards.
commit-message
Conventional Commits: reads the staged diff and proposes type(scope): summary, with body/footer when needed. One logical change = one commit. commit-agent-csk applies it.
trace-scan
Trace scan (§4.1/§4.2): before a commit, scans the staged changes and the message for AI traces (co-author trailers, footers, robot emoji, tool names) and vendor template names. The git hooks apply it automatically.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
gamedev-hotfix
Emergency fix workflow that bypasses normal sprint processes with a full audit trail. Creates hotfix branch, tracks approvals, and ensures the fix is backported correctly.