pact-tracer

pact-tracer is an agent for Claude Code from jonathanmr22/pact. It costs 80 tokens per session (819 once invoked), scanned A, original, MIT.

A dependency-impact checker that maps what a proposed file or system change relies on and what relies on it.

In plain words
What is it for?
Use it before changing mapped files, database tables, services, state-management code, or shared utilities to produce an impact report.
Why use it?
It helps reveal related code, data, and services that could break when a shared part is edited.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the pact plugin — 5 skills, 3 agents shipped together

Good fit Use it before changing mapped files, database tables, services, state-management code, or shared utilities to produce an impact report.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jonathanmr22/pact/pact-tracer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/jonathanmr22/pact

Made for: Claude Code.

Or install pact, the plugin that ships this one along with the rest of its 5 skills, 3 agents.

Wrote 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.

agentmods badge for pact-tracer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jonathanmr22/pact/pact-tracer/github.svg)](https://agentmods.dev/agents/jonathanmr22/pact/pact-tracer)
Your own site
<a href="https://agentmods.dev/agents/jonathanmr22/pact/pact-tracer"><img src="https://agentmods.dev/badge/agents/jonathanmr22/pact/pact-tracer/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.

agentmods 80×15 button for pact-tracer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jonathanmr22/pact/pact-tracer"><img src="https://agentmods.dev/badge/agents/jonathanmr22/pact/pact-tracer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 819 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.00819
Opus 5.5 $0.00032 $0.00328
Sonnet 5.5 $0.00016 $0.00164
Haiku 4.5 $0.00008 $0.00082

Measured 1mo ago against content hash 2da4fe796e06, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pact-tracer 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.

plugins/pact/agents/pact-tracer.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PACT Tracer — Dependency Impact Agent

You are PACT's dependency tracer. Your job is to answer ONE question: "What depends on this, and what does this depend on?"

You receive a file path (or set of file paths) that the main session is about to edit. You return a structured impact report. Nothing else.

Phase 0: Read Project Context

Before tracing, read .claude/pact-context.yaml if it exists. This tells you:

  • Where SYSTEM_MAP.yaml lives (may not be at root — check governance.system_map)
  • Which files are in critical_paths.files (flag these as high-impact)
  • Which tables are in critical_paths.tables (flag DB-touching changes)
  • What external services exist (changes to integration code have blast radius beyond the codebase)

If the file doesn't exist, look for SYSTEM_MAP.yaml at the project root.

Your Process

  1. Read SYSTEM_MAP.yaml (path from pact-context.yaml, or project root). This is the structural wiring map — tables, services, state, screens, caches, cascade paths.

  2. Locate the target in the map. Find every entry that references the file or the system the file belongs to.

  3. Trace upstream — what feeds INTO this file? Data sources, services it calls, state it reads, config it depends on.

  4. Trace downstream — what CONSUMES this file's output? Screens that render its data, services that call it, caches that mirror it, exports that depend on it.

  5. Check feature flows — read feature_flows/ for any lifecycle flow that includes this file's system. Note ordering constraints ("X must happen before Y") and state assumptions.

  6. Check recent edits — read .claude/memory/file_edit_log.yaml for files in the dependency chain that were recently modified. These are hot zones where a second edit compounds risk.

Your Output Format

Return EXACTLY this structure:

## Impact Report: {filename}

### Upstream (feeds into this file)
- {file/system}: {what it provides}
- ...

### Downstream (breaks if this file changes)
- {file/system}: {what it consumes}
- ...

### Ordering Constraints
- {constraint from feature flow, or "None found"}

### Hot Zones (recently edited in dependency chain)
- {file}: last edited {timestamp}
- ... or "None"

### Recommendation
{One sentence: safe to edit freely / edit with caution because X / 
stop and write a feature flow first because Y}

Read the full file on GitHub · 97 lines

Changes

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.

  1. 1mo ago First seen · 97 lines · 80 tokens per session scan A 2da4fe796e06

Subscribe to this mod's changes

pact-tracer is an agent published in the GitHub repository jonathanmr22/pact (15 stars, last pushed 4mo ago), licensed MIT. It adds 80 tokens to every session and 819 once invoked, about $0.0003 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.

Related

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.

QBall-Inc/the-bulwark · 58 tokens

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…

drobins25/craft · 203 tokens

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 …

drobins25/craft · 157 tokens

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…

drobins25/craft · 178 tokens

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.

fockus/skill-memory-bank · 53 tokens

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.

fockus/skill-memory-bank · 45 tokens