pi-agents-config: Skill for Claude Code

.pi/agent/skills/repotrace/SKILL.md

repotrace is a skill for Claude Code, Codex from niclejeune/pi-agents-config. It costs 49 tokens per session (619 once invoked), scanned A, original, MIT.

A local code-navigation tool that builds a focused map of a repository and its relationships before an agent reads or changes many files.

In plain words
What is it for?
Use it to explore a repository, find symbols and their callers, trace call paths, assess change impact, detect dependency cycles, and prepare focused context for code changes.
Why use it?
It reduces aimless browsing in unfamiliar projects and helps reveal which files, functions, callers, and dependencies matter for a task.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

This is niclejeune/pi-agents-config's own configuration. It tells Claude Code and Codex how to work on pi-agents-config itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pi-agents-config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to niclejeune/pi-agents-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/niclejeune/pi-agents-config/main/.pi/agent/skills/repotrace/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/niclejeune/pi-agents-config

Made for: Claude Code, Codex.

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 repotrace

README.md
[![agentmods](https://agentmods.dev/badge/skills/niclejeune/pi-agents-config/repotrace/github.svg)](https://agentmods.dev/skills/niclejeune/pi-agents-config/repotrace)
Your own site
<a href="https://agentmods.dev/skills/niclejeune/pi-agents-config/repotrace"><img src="https://agentmods.dev/badge/skills/niclejeune/pi-agents-config/repotrace/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 repotrace

Your own site · 80×15
<a href="https://agentmods.dev/skills/niclejeune/pi-agents-config/repotrace"><img src="https://agentmods.dev/badge/skills/niclejeune/pi-agents-config/repotrace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 619 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 $0.00049 $0.00619
Opus 5 $0.00024 $0.00309
Sonnet 5 $0.00010 $0.00124
Haiku 4.5 $0.00005 $0.00062

Measured 12d ago against content hash 5f136cc305c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

repotrace 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 12d 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.

.pi/agent/skills/repotrace/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

repotrace Skill

Use repotrace as the default local code intelligence layer for repositories. It is a CLI that works with any coding agent; this workflow uses it with pi agents.

Public repo: https://github.com/niclejeune/repotrace

When to use

Use this before reading many files or making nontrivial code changes:

  • entering an unfamiliar repo
  • implementing a feature touching multiple files
  • debugging unclear behavior
  • reviewing impact/blast radius
  • checking architecture risk before edits
  • finding symbols, callers, callees, routes, or dependency cycles
  • generating a small context bundle for a worker/subagent

Do not bulk-read the repo first when repotrace can give a focused map.

Default workflow

From the target repository root:

repotrace index .
repotrace check --no-fail
repotrace context "<task description>" --print

Only read the files listed in the bundle first. Widen scope only after a concrete reason appears.

Common commands

repotrace overview
repotrace find <query>
repotrace symbol <name>
repotrace callers <symbol>
repotrace callers <symbol> --broad
repotrace callees <symbol>
repotrace file <path>
repotrace impact <file-or-symbol>
repotrace routes
repotrace deps
repotrace cycles
repotrace check --no-fail
repotrace changed --since main

Use global JSON before the subcommand:

repotrace --json check --no-fail
repotrace --json context "<task>" --print

How to interpret checks

repotrace check currently flags:

  • error: Python import cycles
  • error: production code importing test code
  • warning: large production files
  • warning: high fan-in production modules

Warnings are not automatic blockers, but they mean edits need more care and likely tests.

Agent behavior rule

For any nontrivial code task, prefer this sequence:

  1. repotrace index .
  2. repotrace check --no-fail
  3. repotrace context "<task>" --print
  4. Read only the listed files first.
  5. Use repotrace callers, callees, impact, deps, or cycles before widening context.
  6. Report any check errors/warnings that affect the task.

Read the full file on GitHub · 88 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. 12d ago First seen · 88 lines · 49 tokens per session scan A 5f136cc305c8

Subscribe to this mod's changes

repotrace is a skill published in the GitHub repository niclejeune/pi-agents-config (1 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 619 once invoked, about $0.0002 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.