cowork-forge: Skill for Claude Code

.agents/skills/repomix-context-skill/SKILL.md

repomix-context-skill is a skill for Claude Code, Codex from sopaco/cowork-forge. It costs 40 tokens per session (753 once invoked), scanned A, original, MIT.

A guide for reading a local, searchable snapshot of a project's source code. The snapshot is stored in `.terrain/agent/repomix.md` and is regenerated by Terrain, the project's indexing tool.

In plain words
What is it for?
Use it to locate handlers, types, routes, and cross-file implementation details after first reading the project's architecture notes.
Why use it?
It helps an agent find relevant code without loading the entire project into memory, while keeping searches focused on specific files and symbols.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is sopaco/cowork-forge's own configuration. It tells Claude Code and Codex how to work on cowork-forge 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 cowork-forge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sopaco/cowork-forge. 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/sopaco/cowork-forge/main/.agents/skills/repomix-context-skill/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sopaco/cowork-forge

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 repomix-context-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/sopaco/cowork-forge/repomix-context-skill.svg)](https://agentmods.dev/skills/sopaco/cowork-forge/repomix-context-skill)
Your own site
<a href="https://agentmods.dev/skills/sopaco/cowork-forge/repomix-context-skill"><img src="https://agentmods.dev/badge/skills/sopaco/cowork-forge/repomix-context-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 753 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00040 $0.00753
Opus 5 $0.00020 $0.00377
Sonnet 5 $0.00008 $0.00151
Haiku 4.5 $0.00004 $0.00075

Measured 8d ago against content hash 30a8386e6991, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

repomix-context-skill 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 8d 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.

.agents/skills/repomix-context-skill/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repomix Context Skill

Terrain stores a local repomix index at .terrain/agent/repomix.md (gitignored, fast to regenerate).

Read architecture first via terrain-knowledge-skill.terrain/agent/context.md.

When to use

  • Implementation details after reading context.md
  • Cross-file symbol search within the indexed snapshot
  • Locating handlers, types, routes

Query strategy (mandatory)

  1. Read meta.terrain/agent/meta.json (total_tokens, synced_at, top_files_by_tokens)
  2. Search the pack — never load the entire file:
    # <rtk> = ~/.terrain/bin/rtk or bunx @terrain-ai/rtk (see rtk-skill)
    <rtk> grep "struct ProjectOverview" .terrain/agent/repomix.md
    <rtk> grep "### src/lib/api.ts" .terrain/agent/repomix.md
    
    Or agent Grep limited to that path with tight patterns.
  3. Read slices — extract matching ### path/to/file sections only:
    <rtk> read .terrain/agent/repomix.md -l aggressive
    
    Then read the specific ### file block (line range), ≤150 lines per read.
  4. Refresh — if meta.json.synced_at is stale, ask user to run Terrain 重建源码索引 / scan

Repomix section format

Sections look like:

### src/lib/foo.ts

\`\`\`typescript
... file content ...
\`\`\`

Grep for ### relative/path to jump to a file.

Paths

File Purpose
.terrain/agent/repomix.md Full indexed snapshot (local only)
.terrain/agent/meta.json Pack metrics
.terrain/agent/context.md Architecture (read first)

Do not

  • Commit or assume repomix.md exists in git
  • cat / Read the entire repomix.md (can be 100k+ tokens)
  • Read the live repository tree when the pack covers the question
  • Skip context.md and grep source for architecture questions

Regenerate index

If repomix.md is missing:

# bash / Git Bash — <terrain> = ~/.terrain/bin/terrain or bunx @terrain-ai/cli
if [ -x ~/.terrain/bin/terrain ] || [ -x ~/.terrain/bin/terrain.exe ]; then
  ~/.terrain/bin/terrain assets pack-agent .
else
  bunx @terrain-ai/cli assets pack-agent .
fi
# or from repo root in Terrain UI: 重建源码索引

Read the full file on GitHub · 85 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. 8d ago First seen · 85 lines · 40 tokens per session scan A 30a8386e6991

Subscribe to this mod's changes

repomix-context-skill is a skill published in the GitHub repository sopaco/cowork-forge (92 stars, last pushed 13d ago), licensed MIT. It adds 40 tokens to every session and 753 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 2026-08-30.

Related

Other skills, from other repositories

wiki

LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model).

Yeachan-Heo/oh-my-claudecode · 19 tokens

remember

Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.

Yeachan-Heo/oh-my-claudecode · 20 tokens

memory

Persistent, token-efficient project memory. When ON, maintains a .shob/memory/ folder of structured .md files so the full context of the project is NEVER lost across responses, sessions, or context compaction. Uses progressive disclosure — routes through a lightweight INDEX and loads only the files a task needs…

shobcoder/shob · 146 tokens

deja-search

Search deja before re-deriving past work: when the user refers to earlier sessions or decisions, before debugging an error, and before implementing something that may already exist. It searches this machine's own history across every AI coding tool used on it, going back further than deja itself was installed.

vshulcz/deja-vu · 57 tokens

general

Handle everyday conversation, answer questions, manage files, take notes, run scripts, and maintain persistent memory across sessions. Use when the user asks a general question, requests file operations, wants to brainstorm ideas, needs to-do tracking, asks you to remember something, or requests skill search and…

0xranx/golembot · 61 tokens

deja-history

Search the user's past AI coding sessions. Use when they say things like 'didn't we fix this before', 'what did we decide about X', or before re-debugging an error that may already be solved.

vshulcz/deja-vu · 47 tokens