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 skills/zhusq20/claude_engineering/agent-engineering-initnpx skills add zhusq20/claude_engineering --skill agent-engineering-initgit clone --depth 1 https://github.com/zhusq20/claude_engineeringWrote 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/zhusq20/claude_engineering/agent-engineering-init)<a href="https://agentmods.dev/skills/zhusq20/claude_engineering/agent-engineering-init"><img src="https://agentmods.dev/badge/skills/zhusq20/claude_engineering/agent-engineering-init.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 | $0.00136 | $0.01120 |
| Opus 5 | $0.00068 | $0.00560 |
| Sonnet 5 | $0.00027 | $0.00224 |
| Haiku 4.5 | $0.00014 | $0.00112 |
Grade C, and why
agent-engineering-init scanned grade C with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/settings.json # hook config resolves Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/ # bootstrap review housekeeping verify How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Engineering Init
Scaffold a complete, reusable agent-engineering structure into a target repo:
the three-tier layout (.agents/ source of truth → .claude/ symlink view →
.agents_workspace/ state), CLAUDE.md, four core stack-agnostic skills
(bootstrap, review, housekeeping, verify), generic knowledge files, a
SessionStart/PreToolUse hook config, and optional pre-commit config.
This skill ships an init.sh next to this SKILL.md that does the heavy lifting.
Step 1: Gather parameters (use AskUserQuestion)
Determine and confirm with the user:
- Target repo — the directory to scaffold into (default: current working dir, or the argument passed to the skill). Confirm it is the intended repo root.
- Project name — used in
CLAUDE.md(default: repo directory name). - Primary language / lint backend —
ruff(Python) wires up a working commit-time lint gate;nonewrites a clearly-marked placeholder hook for the user's stack. Ask which fits. - Write
.pre-commit-config.yaml? — yes by default; skip if the repo already has its own.
If the repo already contains .agents/skills, ask whether to overwrite (--force)
or abort.
Step 2: Run the scaffolder
From the directory containing this skill, run init.sh against the target:
bash <skill-dir>/init.sh \
--target "<TARGET_REPO>" \
--name "<PROJECT_NAME>" \
--lint "<ruff|none>" \
[--no-precommit] [--force]
init.sh is idempotent-safe: it refuses to clobber an existing .agents/ without
--force, appends to .gitignore rather than overwriting, and never destroys
.agents_workspace/.
Step 3: Verify
cd "<TARGET_REPO>"
ls -l .claude/ # skills, knowledge, hooks, settings.json -> symlinks
ls .claude/skills/ # bootstrap review housekeeping verify
cat .claude/settings.json # hook config resolves
test -d .agents_workspace && echo "workspace OK"
Confirm every symlink resolves (no "broken symlink"), and that
.claude/knowledge/constraints.md is readable through the link.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 102 lines · 136 tokens per session scan C 3fee2ab9659e
agent-engineering-init is a skill published in the GitHub repository zhusq20/claude_engineering (2 stars, last pushed 3mo ago), licensed MIT. It adds 136 tokens to every session and 1,120 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
git-commit
Generate well-formatted git commit messages following conventional commit standards.
test-repo
Use this skill to test strategy changes against a fresh test repository. Invoke when the user asks to "test against a test repo", "validate the changes", or wants to verify session hooks, commits, and checkpoint creation work correctly.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
commit
Commit current changes with a clear, descriptive message.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…