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/luisfelipemoro/harness-devkit/checkcommentsnpx skills add LuisFelipeMoro/Harness-devkit --skill checkcommentsgit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWhat 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 | $0.00058 | $0.00429 |
| Opus 5 | $0.00029 | $0.00215 |
| Sonnet 5 | $0.00012 | $0.00086 |
| Haiku 4.5 | $0.00006 | $0.00043 |
Grade A, and why
checkcomments 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.
What it actually says
checkcomments
List all open comments on the current branch's PR, grouped by file. No actions taken, no files modified.
Contract
Inputs: the current git branch (used to resolve the open PR); a repo with gh authenticated.
Outputs: a printed report — the PR URL, inline comments grouped by file and sorted by line, then general PR comments. No files written, no API mutations.
Boundary: does NOT reply to, resolve, or create comments; does NOT modify code, branches, or the PR.
Dependencies (verify before starting):
gh— GitHub CLI, authenticated; used to resolve the PR and read comments viagh api.git— to read the current branch name.
Steps
- Verify prerequisites —
gh auth status; stop if not authenticated. - Get the current branch (
git branch --show-current); stop if detached HEAD. - Find the open PR for that branch; stop if none — report "No open PR found".
- Resolve
OWNERandREPO. - Fetch inline review comments (
pulls/.../comments). - Fetch general PR comments (
issues/.../comments). - Display: PR URL, inline comments grouped by file and sorted by line, then general comments.
Exact commands, API field handling, alignment rules, and the output example: references/procedure.md.
Machine-checkable behavior contract: skill.spec.yml (route, dependencies, closure, trace).
Done when: the PR URL and both comment sections are printed (each section shows its "No … comments." line when empty). If no open PR resolves for the branch, stop and report that instead of printing an empty report.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 34 lines · 58 tokens per session scan A 3599d8c17750
checkcomments is a skill published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 429 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
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.