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/buildoak/fieldwork-skills/agents-mdgit clone --depth 1 https://github.com/buildoak/fieldwork-skillsWrote 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/buildoak/fieldwork-skills/agents-md)<a href="https://agentmods.dev/instructions/buildoak/fieldwork-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/buildoak/fieldwork-skills/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 | $0.00712 | $0.00712 |
| Opus 5 | $0.00356 | $0.00356 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
fieldwork-skills 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 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fieldwork-skills Agent Installation Guide
fieldwork-skills is a collection of AI agent skills by buildoak. Each skill lives in skills/<skillname>/ and includes a SKILL.md runbook plus update metadata.
Critical Runtime Rules
- Codex CLI reads instructions from the repository root
AGENTS.mdonly. - Codex CLI does not read
codex.mdand does not read.codex/skills/. - Claude Code reads skills from
.claude/skills/<skillname>/SKILL.md.
List Available Skills
Skills are the folders inside skills/.
ls -1 skills/
Current skills:
agent-muxbrowser-opschatgpt-searchgoogle-workspace-opsgsd-coordinatorimage-gensummarizetrueskill-rankvaultweb-search
Install One Skill
Replace <skillname> with a folder name from skills/.
Claude Code:
mkdir -p /path/to/your-project/.claude/skills
cp -R skills/<skillname> /path/to/your-project/.claude/skills/<skillname>
Codex CLI (append this skill's instructions to the target project's root AGENTS.md):
touch /path/to/your-project/AGENTS.md
{
echo
echo "<!-- fieldwork-skill:<skillname> -->"
cat skills/<skillname>/SKILL.md
} >> /path/to/your-project/AGENTS.md
Install All Skills
Claude Code:
mkdir -p /path/to/your-project/.claude/skills
for d in skills/*/; do
cp -R "$d" "/path/to/your-project/.claude/skills/$(basename "$d")"
done
Codex CLI (append all skill runbooks into the target project's root AGENTS.md):
touch /path/to/your-project/AGENTS.md
for f in skills/*/SKILL.md; do
skill="$(basename "$(dirname "$f")")"
{
echo
echo "<!-- fieldwork-skill:${skill} -->"
cat "$f"
} >> /path/to/your-project/AGENTS.md
done
Install Runtime Dependencies
After copying skill folders, read each skill's SKILL.md for runtime dependency setup. Skills may require brew packages, pip packages, npm packages, API keys, or other prerequisites. Each SKILL.md has a "Setup" section with the specific instructions. For a detailed walkthrough, see references/installation-guide.md inside each skill directory.
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 · 102 lines · 712 tokens per session scan A 6aaad550d1d1
fieldwork-skills AGENTS.md is an instructions file published in the GitHub repository buildoak/fieldwork-skills (15 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 712 tokens to every session, about $0.0036 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.
Other instructions, from other repositories
browser-use CLAUDE.md
Claude Code instructions for browser-use/browser-use, covering claude.md, high-level architecture, core components, event-driven browser management and cdp integration.
stealth-browser-mcp AGENTS.md
Instructions for vibheksoni/stealth-browser-mcp, covering agent instructions, start here, recommended proxy services, environment and validation.
Uni-CLI AGENTS.md
AGENTS.md instructions for olo-dot-io/Uni-CLI, covering uni-cli, agent routing rule, always-on writing rule, what you can do and web (183+ sites).
cloakbrowser-mcp AGENTS.md
AGENTS.md instructions for swimmwatch/cloakbrowser-mcp, covering agents.md, about the project, golden rules, project layout and daily commands.
cloakbrowser-mcp copilot-instructions.md
Copilot instructions for swimmwatch/cloakbrowser-mcp: Follow AGENTS.md for project-wide coding, testing, documentation, changelog, and commit rules.
empir3-bridge AGENTS.md
AGENTS.md instructions for empir3hq/empir3-bridge, covering empir3 bridge — agent & contributor guide, what lives here, before you edit, run locally and release / publish.