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 mattbaconz/signal --skill signal-reviewgit clone --depth 1 https://github.com/mattbaconz/signalWrote 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/mattbaconz/signal/signal-review)<a href="https://agentmods.dev/skills/mattbaconz/signal/signal-review"><img src="https://agentmods.dev/badge/skills/mattbaconz/signal/signal-review/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/mattbaconz/signal/signal-review"><img src="https://agentmods.dev/badge/skills/mattbaconz/signal/signal-review.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 | $0.00083 | $0.01398 |
| Opus 5 | $0.00042 | $0.00699 |
| Sonnet 5 | $0.00017 | $0.00280 |
| Haiku 4.5 | $0.00008 | $0.00140 |
Grade A, and why
signal-review 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 12d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚡ signal-review — Templated Code Review
One line per issue. Severity required. Summary at the end. No prose.
Invocation Triggers
Activate when user says any of:
/signal-review"review this","review my code","review this file""check this PR","code review","look at this diff""what's wrong with this","any issues with this code"
Target can be: a file, a diff, a PR URL, a code block, or the current working directory.
Slash command behavior
If the user's message is only /signal-review, treat that as review now.
- Do not stop after acknowledging the skill.
- Do not ask for confirmation unless the user explicitly asked for draft / dry behavior.
- Immediately inspect the provided target (or current working context) and output the review in the format below in the same turn.
Output Format
One line per issue:
{file}:{line}|{issue}|{severity:1-5}|{fix}
Full example:
auth.js:47|nullref on empty arr|4|add guard clause before map
api.js:103|missing await on async call|5|add await
utils.js:12|unused import lodash|1|remove import
∑ 3 issues [1×sev5, 1×sev4, 1×sev1] critical→api.js:103
Rules:
- Severity is required on every line. No exceptions.
- Issue description: max ~60 chars, imperative noun phrase ("nullref on empty arr", not "there is a null reference error")
- Fix: max ~50 chars, imperative ("add guard clause before map", not "you should add a guard clause")
- Order by severity descending (sev5 first)
- One summary line at the end, always
Summary Line Format
∑ {N} issues [{breakdown}] critical→{highest-sev-location}
Examples:
∑ 5 issues [2×sev5, 1×sev3, 2×sev1] critical→auth.js:47
∑ 1 issue [1×sev2]
∑ 0 issues ✓
If zero issues: output only ∑ 0 issues ✓. No explanation, no praise.
Severity Scale
Full definitions in references/severity.md. Quick reference:
| Level | Meaning |
|---|---|
5 |
Breaks in production, security vulnerability, data loss |
4 |
Likely runtime error, will crash under normal use |
3 |
Wrong behavior under specific conditions, logic error |
2 |
Code smell, maintainability issue, confusing pattern |
1 |
Style, minor cleanup, nitpick |
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.
- 12d ago First seen · 171 lines · 83 tokens per session scan A 081920f9f7e7
signal-review is a skill published in the GitHub repository mattbaconz/signal (10 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 1,398 once invoked, about $0.0004 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
simplify
This skill should be used when the user asks to "simplify", "clean up the diff", "run simplify", "simplify the changes", "review changed code for cleanup", explicitly invokes "/simplify", or asks to "commit without simplify", "skip simplify for this commit", or "commit this but skip simplify". Reviews changed code…
resolve-pr-comments
This skill should be used when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR issues", "respond to PR review", or explicitly invokes "resolve-pr-comments".
review-pr
This skill should be used when user asks to "review a PR", "review pull request", "review this pr", "code review this PR", "check PR.
lov-code-review
A code review assistant that examines a real code change for defects, security problems, and maintenance risks. A code review is a check of proposed changes before they are accepted.
adversarial-refinement-loop
Run a persistent adversarial research, critique, implementation, and verification loop until the user stops it. Invoke only when the user explicitly asks for this skill or an indefinite refinement loop.
adr-review
Review an ADR the user has written in docs/adr/. Use when the user says an ADR is ready for review or asks for feedback on a decision record. Never use this to write or rewrite an ADR for them.