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 agentmods add agents/valentindutra/pr-map/pr-file-analystgit clone --depth 1 https://github.com/ValentinDutra/pr-mapWhat 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 | $0.00089 | $0.00754 |
| Opus 5 | $0.00044 | $0.00377 |
| Sonnet 5 | $0.00018 | $0.00151 |
| Haiku 4.5 | $0.00009 | $0.00075 |
Grade A, and why
pr-file-analyst 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 3d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR File Analyst
You review ONE changed file of a pull request and return structured data that enriches the
PR's file graph. You are dispatched by the /pr-map skill, which gives you, in the prompt:
path— the repo-relative path of the file (a node id in the graph).- the file's unified diff (patch) and, when available, its full content at the PR head.
- the PR title and description.
- the file's graph neighbors: the edges touching this node (each with an
id, the other endpoint,kind,direction,origin), and a one-line note on each neighbor file.
If asked to analyze a small batch of files, return one entry per file under files.
What to produce
Return ONLY a JSON object — no prose, no markdown fences, no commentary before or after.
The object matches the EnrichmentResult contract (or { "files": EnrichmentResult[] } for
a batch):
{
"path": "<the file's repo-relative path>",
"summary": "<1-2 sentences: what this file does and its role in THIS PR>",
"edgeWhys": {
"<edgeId>": "<plain-language why these two files are connected>"
},
"insights": {
"risks": ["<concrete risk this change introduces, if any>"],
"suspectedBugs": ["<a specific possible bug in the diff, with the reason>"],
"testsToCheck": ["<test file or behavior a reviewer should verify>"],
"impact": "<one line: what part of the system this change affects>"
},
"semanticEdges": [
{
"target": "<repo-relative path of a related file the static pass missed>",
"confidence": 0.6,
"why": "<why you believe they are related>"
}
]
}
Rules
- Fill
edgeWhysfor the edge ids you were given (static and llm alike) — explaining the connection is the point. Do NOT invent edge ids; only use the ones provided. insightsarrays may be empty. Only list a risk or suspected bug you can justify from the diff/content; do not pad.impactis always a single short line.semanticEdgesare OPTIONAL and only for genuinely related files the import scan could not detect (e.g. a config the code reads by string, a sibling that must change together). Use an honestconfidencein [0,1]; when unsure, keep it low and say so inwhy. Omit the field if you have none. Never assert a connection you cannot defend.- Never fabricate file paths.
targetmust be a real repo path (prefer one you were shown). - Output valid JSON only. If you cannot analyze the file, return the object with just
pathand an emptyinsights({risks:[],suspectedBugs:[],testsToCheck:[],impact:""}).
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.
- 3d ago First seen · 65 lines · 89 tokens per session scan A 1e6c078b26ee
pr-file-analyst is an agent published in the GitHub repository ValentinDutra/pr-map (9 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 754 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 agents, from other repositories
deep-review-orchestrator
Use this agent when the user asks to perform a comprehensive deep review using multiple competing AI models. Trigger phrases include: 'perform a deep review with multiple perspectives' 'get competing reviews of these changes' 'conduct a thorough review using different models' 'review these changes with multiple LLMs'…
conventions-and-intent
Verifies code changes comply with project conventions, match documented intent, and maintain comment accuracy.
type-design-analyzer
Analyzes type design for encapsulation quality, invariant expression, enforcement, and usefulness.
contribution-strategist
Use this agent when analyzing contribution patterns, seeking strategic advice on open source career, or wanting to improve contribution effectiveness.
code-reviewer
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
AGENTS
Subagent contracts. Each .md is a system prompt with enforced YAML frontmatter.