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 skills add sergei-aronsen/claude-code-toolkit --skill repomixgit clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkitWrote 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.
[](https://agentmods.dev/skills/sergei-aronsen/claude-code-toolkit/repomix)<a href="https://agentmods.dev/skills/sergei-aronsen/claude-code-toolkit/repomix"><img src="https://agentmods.dev/badge/skills/sergei-aronsen/claude-code-toolkit/repomix/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.
<a href="https://agentmods.dev/skills/sergei-aronsen/claude-code-toolkit/repomix"><img src="https://agentmods.dev/badge/skills/sergei-aronsen/claude-code-toolkit/repomix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00073 | $0.01844 |
| Opus 5.5 | $0.00029 | $0.00738 |
| Sonnet 5.5 | $0.00015 | $0.00369 |
| Haiku 4.5 | $0.00007 | $0.00184 |
Grade A, and why
Repomix 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.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repomix Skill
Load this skill when packing repositories for AI consumption — local or remote. Repomix bundles a codebase into a single XML/Markdown/JSON file, with optional tree-sitter compression that keeps signatures and drops bodies.
Rule
REPOMIX IS FOR BREADTH, NOT DEPTH.
It gives an LLM a wide signatures-level view of the whole codebase. It is not a substitute for reading one file carefully or grepping for one function. Use the right tool for the job.
When To Use Repomix
| Task | Tool | Why |
|---|---|---|
| Find one function definition | find-function or Grep |
Repomix overshoots — 1000 files for 1 symbol |
| Read a specific file | Read |
Direct, exact, no subprocess |
| Open exploration over 2-3 files | Explore agent |
Built-in budget control |
| Architectural review across the whole repo | Repomix --compress |
Signatures of every module, fits LLM context |
| Hand the codebase to ChatGPT / web Claude / Gemini | Repomix → clipboard | One file, formatted for LLMs |
| Compare two upstream revisions | Repomix --remote --remote-branch |
No clone needed |
| Council needs full-codebase context | brain --pack (automatic in v6.23+) |
Already wired in |
| Attach codebase to a GitHub issue / PR | Repomix --style markdown |
Renders nicely on GitHub |
If the task isn't on the "use" rows above — pick a sharper tool.
How To Invoke
From inside Claude Code
/pack # current repo, defaults
/pack --remote yamadashy/repomix # remote
/pack --include "src/**" --format md # subset + markdown
/pack --to clipboard # copy, don't write a file
The /pack command is the supported entry point. It writes to
.claude/scratchpad/pack-<timestamp>.<ext>.
From your shell
# Pack this repo
npx -y [email protected] --compress --style xml
# Pack a remote repo
npx -y [email protected] --remote nestjs/nest --compress --style markdown --output /tmp/nest.md
# Pack a specific commit of an upstream repo
npx -y [email protected] \
--remote yamadashy/repomix \
--remote-branch 5811266e6f242c6f30ad102a066acf7780dcbf30 \
--compress
# Pack only changed files (pipe from git)
git ls-files '*.ts' | npx -y [email protected] --stdin --stdout
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.
- 1mo ago First seen · 206 lines · 73 tokens per session scan A e8a4b5cf54f2
Repomix is a skill published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 1,844 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…