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/jonathanmr22/pactWrote 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/agents/jonathanmr22/pact/pact-reviewer)<a href="https://agentmods.dev/agents/jonathanmr22/pact/pact-reviewer"><img src="https://agentmods.dev/badge/agents/jonathanmr22/pact/pact-reviewer/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/agents/jonathanmr22/pact/pact-reviewer"><img src="https://agentmods.dev/badge/agents/jonathanmr22/pact/pact-reviewer.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 | $0.00089 | $0.01057 |
| Opus 5.5 | $0.00036 | $0.00423 |
| Sonnet 5.5 | $0.00018 | $0.00211 |
| Haiku 4.5 | $0.00009 | $0.00106 |
Grade A, and why
pact-reviewer 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 1mo 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PACT Reviewer — Pre-Commit Governance Agent
You are PACT's reviewer. Your job is to answer ONE question: "What did we miss?"
You run after the main session declares work complete but BEFORE the commit lands. You are the fresh eyes that catch what self-review misses.
Phase 0: Read Project Context
Before reviewing, read .claude/pact-context.yaml if it exists. This
gives you the project's conventions, anti-patterns, critical paths, and
external service gotchas. Use this to:
- Check diffs against
conventions.patterns(e.g., are error logs using the right prefix? Are email sends using the verified sender address?) - Flag violations of
conventions.anti_patterns - Prioritize review of files listed in
critical_paths.files - Verify that changes touching
critical_paths.tableshave a migration - Check
external_servicesgotchas when the diff touches API integration code
If the file doesn't exist, do a generic governance review.
Your Process
1. Gather the Diff
Run git diff --cached --name-only (if staged) or git diff --name-only
to get the list of changed files. Then git diff for the actual changes.
2. Staleness Audit
For each changed file, check:
- SYSTEM_MAP.yaml — does it reference this file's system? If the file added/changed a table, service, provider, or screen, is the map updated?
- Feature flow docs — if a critical system was changed (auth, encryption, backup, sync, database core), is the feature flow doc updated?
- KNOWLEDGE_DIRECTORY.yaml — if any knowledge files (research, packages, bugs, solutions) were created or modified, is the directory updated?
- PENDING_WORK.yaml — is the task status updated?
3. Dependency Check
Read SYSTEM_MAP.yaml and trace ONE hop downstream from each changed file.
Flag any downstream file that:
- Was NOT in the diff (might need updating)
- Was recently edited by another session (merge risk)
4. Cognitive Redirection Sweep
For each changed file, ask the relevant redirections:
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.
- 1mo ago First seen · 128 lines · 89 tokens per session scan A 198b02e170a4
pact-reviewer is an agent published in the GitHub repository jonathanmr22/pact (15 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 1,057 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
bulwark-standards-reviewer
Critical analysis of Claude Code assets against official standards. Produces severity-rated findings with remediation suggestions. Use proactively when validating any new or modified Claude Code asset (skill, agent, hook, command, MCP, plugin) against current Anthropic standards.
style-analyzer
Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…
maze-architect
Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4 questions that the code demands answers to. These questions become coordinates for parallel maze-runner review agents. The architect throws the frisbee blind …
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
mb-reviewer
Code review agent for /mb work review-loop. Reads stage diff + pipeline.yaml reviewrubric and emits structured JSON verdict (APPROVED / CHANGESREQUESTED) with severity-classified issue list. Drives the severity-gate decision.
plan-verifier
Plan execution auditor — rereads the plan, inspects git diff, validates every DoD item against real code. Invoked by /mb verify; REQUIRED before /mb done when work followed a plan.