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/lexfrei/ccc/address-pr-commentsnpx skills add lexfrei/ccc --skill address-pr-commentsgit clone --depth 1 https://github.com/lexfrei/cccWrote 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/lexfrei/ccc/address-pr-comments)<a href="https://agentmods.dev/skills/lexfrei/ccc/address-pr-comments"><img src="https://agentmods.dev/badge/skills/lexfrei/ccc/address-pr-comments.svg" alt="Measured on agentmods" 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 | $0.00113 | $0.04122 |
| Opus 5 | $0.00056 | $0.02061 |
| Sonnet 5 | $0.00023 | $0.00824 |
| Haiku 4.5 | $0.00011 | $0.00412 |
Grade A, and why
address-pr-comments 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 4d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL: This skill makes PUBLIC changes — commits pushed to the PR branch and replies visible to the PR author, reviewers, and all watchers. Every commit must follow project conventions (signed off, GPG-signed where configured, conventional message). Every reply must be accurate, justified, and in English.
Arguments
Parse $ARGUMENTS as a space-separated list of PR refs.
- Each ref: bare number (e.g.
2395, uses the repo fromgh repo view --json owner,name) ORowner/repo#N(e.g.cozystack/cozystack#2395). - If no args: fall back to detection from the current branch via
gh pr view --json number,headRepositoryOwner,headRepository --jq '.headRepositoryOwner.login + "/" + .headRepository.name + "#" + (.number|tostring)'— single-PR mode. - If no args and no PR can be inferred: report the error and stop.
Normalize each ref into OWNER, REPO, PR_NUMBER.
Step 0: Record the starting state
Before touching any PR branch:
ORIGINAL_REF=$(git symbolic-ref --quiet --short HEAD || git rev-parse HEAD)
if [ -z "$(git status --porcelain)" ]; then CLEAN_START=1; else CLEAN_START=0; fi
ORIGINAL_REFis the branch to return to at the end.CLEAN_START == 1means the working tree was clean — safe to restore later.- If the working tree is dirty, ask the user how to handle it (abort, stash, or proceed without final restore) BEFORE doing any
git checkout.
Step 1: Outer loop over PR refs
For each PR ref in the parsed list, execute Steps 2–10 in order. Between PRs, print a visible separator (e.g. ────── PR #N ──────) so progress is easy to follow.
On a per-PR unrecoverable error (PR not found, branch push rejected and user chose not to force, etc.): print the error, skip the remaining steps for that PR, continue with the next ref. Do not abort the whole run.
Step 2: Check out the PR branch
PR_BRANCH=$(gh pr view $PR_NUMBER --repo $OWNER/$REPO --json headRefName --jq .headRefName)
git fetch origin "$PR_BRANCH"
git checkout "$PR_BRANCH"
git log --oneline -5
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.
- 4d ago First seen · 297 lines · 113 tokens per session scan A 43b6f672a116
address-pr-comments is a skill published in the GitHub repository lexfrei/ccc (9 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 113 tokens to every session and 4,122 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…