A repository-aware coding-agent skill that uses a `.synrepo` directory to provide prepared information about a codebase before the agent reads source files directly.

Use it when a repository has synrepo context available and you need to investigate or work on its code.

It helps an agent start with compact, structured context about the repository instead of searching through files without guidance.

synrepo — Skill for Claude Code and Codex by whit3rabbit

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.

Any agent

npx skills add whit3rabbit/clean-room-skill --skill synrepo

Clone the repo

git clone --depth 1 https://github.com/whit3rabbit/clean-room-skill

Made for: Claude Code, Codex.

Or install clean-room, the plugin that ships this one along with the rest of its 10 skills, 7 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/whit3rabbit/clean-room-skill/synrepo/github.svg)](https://agentmods.dev/skills/whit3rabbit/clean-room-skill/synrepo)

Your own site

<a href="https://agentmods.dev/skills/whit3rabbit/clean-room-skill/synrepo"><img src="https://agentmods.dev/badge/skills/whit3rabbit/clean-room-skill/synrepo/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/whit3rabbit/clean-room-skill/synrepo"><img src="https://agentmods.dev/badge/skills/whit3rabbit/clean-room-skill/synrepo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,934 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.01934
Opus 5	$0.00006	$0.00967
Sonnet 5	$0.00003	$0.00387
Haiku 4.5	$0.00001	$0.00193

Measured 10d ago against content hash e185f5fb6d87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

synrepo scanned grade B with 1 finding 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 10d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Project-scoped setup writes trusted project `.codex/config.toml`. Global Codex MCP registration is not automated by `synrepo setup`; if you configure `~/.codex/config.toml` manually, launch `synrepo mcp` and pass `repo_r

.agents/skills/synrepo/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

name: synrepo description: Use synrepo in repositories with a .synrepo/ directory. Prefer synrepo cards, compact search, and bounded task contexts before reading source files cold.

synrepo context

synrepo is a local, deterministic code-context compiler. It compiles repository files into observed graph facts, code artifacts, task contexts, and cards/MCP packets before agents read source cold.

Codex setup

This skill belongs at .agents/skills/synrepo/SKILL.md.

Project-scoped setup writes trusted project .codex/config.toml. Global Codex MCP registration is not automated by synrepo setup; if you configure ~/.codex/config.toml manually, launch synrepo mcp and pass repo_root to repo-addressable tools. To add local non-blocking Codex nudges, run synrepo setup codex --agent-hooks.

For project-scoped manual setup, edit trusted project .codex/config.toml directly:

[mcp_servers.synrepo]
command = "synrepo"
args = ["mcp", "--repo", "."]

Agent doctrine

synrepo is a local, deterministic code-context compiler: repo files -> graph facts -> code artifacts -> task contexts -> cards/MCP. In .synrepo/ repos, prefer MCP/CLI over cold reads for questions, reviews, search, impact, and edits.

Default path

For questions, reviews, search routing, and edits: orient, ask or search, cards, impact or risks, edit, tests, changed.

Start with synrepo_orient before reading the repo cold.
Use synrepo_ask for broad plain-language tasks needing one bounded, cited task-context packet.
Use synrepo_find only for bounded file-routing suggestions after broad task context is clear. Use synrepo_search for exact files, symbols, strings, flags, code-shaped errors, and tool names. For broad lexical searches, prefer output_mode: "compact".
Use tiny cards to route and normal cards to understand. Use synrepo_minimum_context once a focal target is known and neighborhood risk is unclear.
Use synrepo_impact (or synrepo_risks) before risky edits or reviews, and synrepo_tests before claiming done.
Use synrepo_changed after edits to review changed context and validation commands.
After stale resumes or lost context, call synrepo_resume_context before asking the user to repeat repo state.
Read full source files or request deep cards only after bounded cards identify the target or prove insufficient.

Read the full file on GitHub · 115 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.

10d ago First seen · 115 lines · 13 tokens per session scan B e185f5fb6d87

Subscribe to this mod's changes

synrepo is a skill published in the GitHub repository whit3rabbit/clean-room-skill (10 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 1,934 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens

synrepo