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 skills add AmineDjeghri/personal-os-setup --skill code-review-triagegit clone --depth 1 https://github.com/AmineDjeghri/personal-os-setupWrote 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/aminedjeghri/personal-os-setup/code-review-triage)<a href="https://agentmods.dev/skills/aminedjeghri/personal-os-setup/code-review-triage"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/code-review-triage/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/aminedjeghri/personal-os-setup/code-review-triage"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/code-review-triage.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 | $0.00018 | $0.00924 |
| Opus 5.5 | $0.00007 | $0.00370 |
| Sonnet 5.5 | $0.00004 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
code-review-triage 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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triaging a review finding on your own code
When to Use
- A bot, linter or human flags
<file>:<line>and proposes a fix, forwarded with "can you check this" / "want a quick patch adding X?". - You notice a defect in a sibling script while working on one the user flagged.
The job is not to apply the suggestion: decide whether the claim is true, how much it matters in this
script's run context, and what the right patch is — then offer it. Reply order: verdict on the claim, priority,
the defects the reviewer missed, then the patch. A patch offered before the verdict reads as agreement.
(Reviewing someone else's PR: github-code-review.)
1. Verify the claim at the cited line
- Confirm the line number, the actual call, and what already protects it. Findings routinely ask for
protection that exists — a bare
except Exceptionis not a "missing exception handler". Say so rather than adding a redundant layer. - An exception handler bounds a failure; a timeout bounds a hang. A bare
exceptnever bounds a hang and a missing timeout never raises. Check which one the claim is about.
2. Grade severity by run context, in one clause
- Interactive, human-watched, one-shot script (a registration helper, a manual sync): a hang is low. The same defect in a pipeline, cron job or unattended script is high. The user decides whether to spend effort on "low".
- "The claim is accurate" is not "the finding is right": if it is mis-prioritized or incomplete, lead with that.
3. Find the real unbounded wait before patching
- The flagged line is rarely the worst. Scan the file for
while, poll/retry loops and recursion: an unbounded poll for an external event (a button press, a device coming online) with no attempt cap strands the user, and a line-oriented reviewer can't see it. - Bound it three ways: an attempt cap whose comment states the wall-clock budget, the request exception caught inside the loop, and a distinct message for exhaustion (the same text as an explicit refusal makes the operator retry the wrong thing).
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.
- yesterday First seen · 69 lines · 18 tokens per session scan A 7262b411ebb5
code-review-triage is a skill published in the GitHub repository AmineDjeghri/personal-os-setup (659 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 924 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-20.
Other skills, from other repositories
wsl-bash-crlf-or-tempfile
When a Windows shell (PowerShell/cmd) feeds a bash script into WSL, CRLF line endings can corrupt the first shell builtin; force LF or pipe via a temp file.
wsl-networking-mode-dns-fallback
When WSL's mirrored networking fails and falls back to "None", plus /etc/wsl.conf has generateResolvConf=false, the distro has no DNS; fix both layers.
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
gsd-ns-review
Invoke this Pi skill with /skill:gsd-ns-review.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.