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-prgit 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-pr)<a href="https://agentmods.dev/skills/mattbaconz/signal/signal-pr"><img src="https://agentmods.dev/badge/skills/mattbaconz/signal/signal-pr/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-pr"><img src="https://agentmods.dev/badge/skills/mattbaconz/signal/signal-pr.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 | $0.00062 | $0.01230 |
| Opus 5.5 | $0.00025 | $0.00492 |
| Sonnet 5.5 | $0.00012 | $0.00246 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
signal-pr 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 2mo 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚡ signal-pr — Commit + Push + PR
One command. Stages, commits, pushes, opens a PR. Done.
Invocation Triggers
Activate when user says any of:
/signal-pr"open a PR","create pull request","ship a PR","make a PR""commit push and PR","PR this"
Slash command behavior
If the user's message is only /signal-pr (optionally with flags like
--dry, --draft, or --pr-draft), treat that as execute now.
- Do not stop after acknowledging the skill.
- Do not ask for confirmation unless the user explicitly requested review mode.
- Immediately run the ordered steps below in the same turn.
- Respect
--dry,--draft, and--pr-draftexactly as defined in this file.
Behavior (Ordered Steps)
-
Run signal-push logic — stages, commits, pushes. See
signal-push/SKILL.mdfor complete push behavior. -
Generate PR title
- Derived from commit message(s)
- Single commit: use commit message as-is
- Multiple commits: synthesize a title covering the change set
- Max 72 chars, same rules as commit messages
-
Generate PR body using this exact template:
## Changes - {change 1} - {change 2} ## Type {feat|fix|refactor|chore|docs|test|style|perf} Closes #{issue_number}- Changes: bullet list derived from diff, grouped by type. No fluff.
- Issue number: extracted from branch name if present (e.g.
feat/PROJ-123-thing→Closes #123) - Omit
Closes #line if no issue number detectable
-
Open the PR
gh pr create --title "{title}" --body "{body}" -
Report
✓ feat(auth): add JWT refresh token rotation [3 files, +47/-12] ✓ pushed → origin/feat/jwt-refresh ✓ PR opened → https://github.com/org/repo/pull/142
PR Body Template
## Changes
- {change 1}
- {change 2}
## Type
{feat|fix|refactor|...}
Closes #{issue_number if detectable from branch name}
Rules:
- Changes are imperative phrases, max 80 chars each: "add JWT refresh token rotation"
- Group by type if multiple types present (feat changes, then fix changes, etc.)
- No prose, no explanation, no "this PR introduces"
- No emoji
What ships with it
3 files 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.
- 2mo ago First seen · 170 lines · 62 tokens per session scan A 0c50a64edfcf
signal-pr is a skill published in the GitHub repository mattbaconz/signal (11 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 1,230 once invoked, about $0.0002 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 2026-08-31.
signal-pr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| signal-prmattbaconz/signal | Skill | 11 | 4mo ago | MIT | A | 62 | Claude Code |
| commit-stagedfcakyon/claude-codex-settings | Skill | 1.2k | today | Apache-2.0 | A | 46 | Claude Code |
| lov-checkpoint-listlovstudio/skills | Skill | 72 | today | MIT | A | 38 | Claude Code |
| lov-git-commit-with-contextlovstudio/skills | Skill | 72 | today | MIT | A | 47 | Claude Code |
| chinese-commit-conventionsLeodorareluctant259/superpowers-zh | Skill | 5 | 27d ago | MIT | A | 28 | Claude Code |
| atomic-commitsAkshitIreddy/agent-skills | Skill | 1 | 1mo ago | MIT | A | 17 | Claude Code, Codex |
| bitbucket-automationrootcastleco/rei-skills | Skill | 7 | today | none | A | 38 | Claude Code, Codex |