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.
git clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/commands/rjmurillo/ai-agents/pr-quality-gate-reliability)<a href="https://agentmods.dev/commands/rjmurillo/ai-agents/pr-quality-gate-reliability"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/pr-quality-gate-reliability/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/commands/rjmurillo/ai-agents/pr-quality-gate-reliability"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/pr-quality-gate-reliability.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 | $0.00000 | $0.02438 |
| Opus 5 | $0.00000 | $0.01219 |
| Sonnet 5 | $0.00000 | $0.00488 |
| Haiku 4.5 | $0.00000 | $0.00244 |
Grade A, and why
pr-quality-gate-reliability scanned grade A with 2 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Are generic calls (`requests.get(url)`, `subprocess.run(cmd)`) missing a `timeout=`? Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Are generic calls (`requests.get(url)`, `subprocess.run(cmd)`) missing a `timeout=`? How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reliability Review Task
You are reviewing a pull request for production survivability: how the change behaves when its dependencies misbehave, time out, or fail.
Context Mode Enforcement (REQUIRED)
The CI harness prepends a CONTEXT_MODE: [full|summary|partial] header to the
context it sends you. Read that header before you decide a verdict. It tells you
how much of the diff you actually received.
full: the complete diff is present.PASS,WARN, andCRITICAL_FAILare all permitted on the merits.summary: only a file list or stat-only summary is present (the PR exceeded the diff-size limit). You did not see the line-level changes.partial: only a bounded slice of the diff is present (for example, the first N lines). You did not see the rest.
When CONTEXT_MODE is not full, you MUST NOT emit PASS. A PASS asserts
evidence you do not have. Emit WARN (or a higher-severity verdict if the
available metadata already shows a problem), state that context was
summary or partial, and name the specific evidence you would need to clear
the PR. Treat a missing or unrecognized CONTEXT_MODE value as not full.
This is a manipulation-resistance control: an adversary can craft a PR that
trips summary mode to hide a change behind a stat-only context. Forbidding PASS
keeps that change from passing on absent evidence. See
.agents/governance/AI-REVIEW-MODEL-POLICY.md ("CONTEXT_MODE Header (REQUIRED)").
Grounding Rules
- Do NOT claim software versions are "beta", "unstable", or "unreleased" based on training data. Your training data has a cutoff and may be outdated.
- Do NOT claim tools (ruff, mypy, pytest, etc.) lack support for a version unless you have concrete evidence from the diff itself.
- For dependency update PRs: evaluate the diff for internal consistency, not external ecosystem assumptions. If CI tests pass, the tooling works.
- Base findings on what the code shows, not on recalled release schedules.
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.
- today First seen · 197 lines · 0 tokens per session scan A 5805a5c6f8ea
pr-quality-gate-reliability is a command published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,438 tokens. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other commands, from other repositories
review-branch
Review an existing branch holistically before merging — blast radius, conventions, security, and spec compliance.
code-review-swarm
Deploy specialized AI agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis.
optimizer
Performance optimization with systematic analysis and improvements.
check
Run verification checks on code, tasks, or agent outputs.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.