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/mollyretter/forward-deployed-engineer-toolkit/claude-mdgit clone --depth 1 https://github.com/mollyretter/forward-deployed-engineer-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/instructions/mollyretter/forward-deployed-engineer-toolkit/claude-md)<a href="https://agentmods.dev/instructions/mollyretter/forward-deployed-engineer-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/mollyretter/forward-deployed-engineer-toolkit/claude-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 | $0.00479 | $0.00479 |
| Opus 5 | $0.00239 | $0.00239 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
forward-deployed-engineer-toolkit CLAUDE.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 5d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repo
Notes for agents (Claude Code) collaborating on forward-deployed-engineer-toolkit. Project-level guidance; user-level writing preferences live in user memory.
Commit and PR conventions
- One gitmoji per commit (unicode preferred, e.g. ✨, ♻️, 🐛, 📋). Do not double up emoji and text code.
- PRs go through
gh pr reviewwith explicit dev approval before any review comment posts publicly.
Skill conventions
- Each skill ships in two shapes: a Claude Code skill (
SKILL.md) and an importable schema/library (schema.tsplus tests). - New skills should follow the directory shape of
skills/north-star/(the prior art). validate-skills.mjsandvitestrun in CI on every PR; both must be green before merge.
Privacy: CI stdout is public, braintrust is private
This repo is public. GitHub Actions logs are public. Braintrust traces are private. Anything any CI script prints to stdout or stderr is durably public.
Rules for CI scripts that touch braintrust data:
- Eval scripts, telemetry scripts, and threshold-check scripts may print only aggregate numbers (counts, precision, recall, percentages, averages). Never:
- PR diff content, even partial
- Agent prompts or responses, even partial
- Finding text, location strings that reference real files, or suggestion text
- Dev decision content (the labels themselves, beyond aggregate counts)
- Any field of a logged trace beyond the trace ID
- If a script needs to indicate which traces it processed, print trace IDs only. Anyone with braintrust access can look up the content; anyone without it sees only opaque identifiers.
- On API errors: print a sanitized error message (e.g.
braintrust API error: status 429), never the request or response bodies. - When in doubt, do not print. Add a comment explaining why a field is intentionally redacted so future maintainers do not "fix" it.
This rule applies to every script under scripts/ and every workflow under .github/workflows/. Skill files (SKILL.md) repeat the rule for the agent's benefit during interactive runs, but the canonical statement is here.
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.
- 5d ago First seen · 33 lines · 479 tokens per session scan A ddd6b645ef5a
forward-deployed-engineer-toolkit CLAUDE.md is an instructions file published in the GitHub repository mollyretter/forward-deployed-engineer-toolkit (9 stars, last pushed 13d ago), licensed MIT. It adds 479 tokens to every session, about $0.0024 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
Skill_Seekers CLAUDE.md
Instructions for yusufkaraaslan/Skill_Seekers, covering claude.md, project overview, essential commands, required before running tests or cli (src/ layout) and run all tests (never skip - all must pass before commits).
FDEOps AGENTS.md
AGENTS.md instructions for suboss87/FDEOps, covering agents.md - working in the fdeops repository, if you are helping use fdeops in an engagement, if you are contributing to this repository and boundaries.
claude-code-toolkit CLAUDE.md
Claude Code instructions for robertguss/claude-code-toolkit, covering claude.md, project overview, build commands, package a single skill for claude.ai upload and package all skills.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
claude-code_dual-boot-skill CLAUDE.md
Instructions for ombulabs/claude-code_dual-boot-skill, covering claude.md, what this repository is, scope: stay inside the dual-boot boundary, invariants this skill teaches (and must not contradict) and working conventions.
obsidian-ai CLAUDE.md
Instructions for spencermarx/obsidian-ai, covering claude.md, project overview, build & development commands, architecture and key design decisions.