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 instructions/jackin-project/jackin-agent-smith/agents-mdgit clone --depth 1 https://github.com/jackin-project/jackin-agent-smithWrote 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/instructions/jackin-project/jackin-agent-smith/agents-md)<a href="https://agentmods.dev/instructions/jackin-project/jackin-agent-smith/agents-md"><img src="https://agentmods.dev/badge/instructions/jackin-project/jackin-agent-smith/agents-md.svg" alt="Measured on agentmods" 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 | $0.01387 | $0.01387 |
| Opus 5 | $0.00694 | $0.00694 |
| Sonnet 5 | $0.00277 | $0.00277 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
jackin-agent-smith AGENTS.md 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 4d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — jackin-agent-smith
A public-friendly Claude Code agent image for code review. Extends the digest-pinned projectjackin/construct:<version>-trixie base with the code-review and feature-dev plugins pre-configured. Layers Node.js on top of the construct base.
Image distribution is public (published to a registry); any user pulling it runs exactly what this Dockerfile builds. Baked-in secrets leak to every puller.
Threat model
Threat surface for this image:
- Base image supply chain.
projectjackin/construct:<version>-trixieis pinned by digest in the Dockerfile. Whoever can push toprojectjackin/constructstill serves the base image, so digest refreshes require review. - Build-time tool pulls.
mise install node@ltshits mise's registry to resolve "lts" at build time. If mise's registry or the pulled Node.js tarball is compromised between releases, this image inherits the compromise. - Runtime credential exposure. The image itself holds no credentials, but operators mount their
~/.config/gh/hosts.yml, Claude Code auth, and sometimes SSH keys into the container at run time. Any plugin or tool running inside has access. The Dockerfile must not cache these paths, ENV them, or bake them into layers. - Layer secrets.
--build-argorENVof sensitive values bakes them into the image, retrievable viadocker history. Currently none are used; any addition requires review. - Plugin trust. All plugins in
jackin.role.tomlcome from@claude-plugins-official. Trust is anchored in that marketplace's maintainers.
Hard rules (do not break these)
- Final stage must use a digest-pinned
projectjackin/construct:<version>-trixiebase. This is the contract jackin enforces; breaking it makes the role unloadable. - Never add a plugin without documenting its trust anchor. Marketplace name alone is insufficient — note in the PR why the specific plugin is trusted. Third-party plugins are lateral attack surface.
- Never
ENV GITHUB_TOKEN=...or any credential ENV. NoARG GITHUB_TOKEN=..., noCOPY ~/.secrets/.... Credentials come from the operator's shell at run time. - No build-time secrets in plain
ARG/ENV. If a step ever needs a secret, use--mount=type=secret. - Never use
latestfor anything pinned.node@ltsis acceptable only because mise resolves it at build time and the--pinflag snapshots the result. - The marketplace allow-list in pre-commit check #3 must stay in sync with
[[claude.marketplaces]]injackin.role.toml. Adding a new marketplace requires updating both, otherwise the audit will flag every plugin from it.
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.
- 4d ago First seen · 82 lines · 1,387 tokens per session scan A 39291354bb5e
jackin-agent-smith AGENTS.md is an instructions file published in the GitHub repository jackin-project/jackin-agent-smith (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,387 tokens to every session, about $0.0069 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 instructions, from other repositories
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
openlakeforge AGENTS.md
Instructions for malon64/openlakeforge, covering agent and contributor guide, what this project is, orientation — read in this order, repository map and architectural rules.
docker-zoneminder CLAUDE.md
Instructions for jantman/docker-zoneminder, covering claude.md, project overview, build and test, ci/cd and architecture.
mitos CLAUDE.md
Instructions for mitos-run/mitos, covering claude.md, project overview, operating principles, commands and architecture.
observability-mcp CLAUDE.md
Instructions for ThoTischner/observability-mcp, covering observability-mcp development guide, docker-first development, quick start, rebuild a single service and view logs.
workshop copilot-instructions.md
Copilot instructions for canonical/workshop, covering github copilot instructions, project overview, tech stack, repository structure and core directories.