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 alessiomarcone/agent-fieldbook --skill promptgit clone --depth 1 https://github.com/alessiomarcone/agent-fieldbookWrote 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/alessiomarcone/agent-fieldbook/prompt)<a href="https://agentmods.dev/skills/alessiomarcone/agent-fieldbook/prompt"><img src="https://agentmods.dev/badge/skills/alessiomarcone/agent-fieldbook/prompt/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/alessiomarcone/agent-fieldbook/prompt"><img src="https://agentmods.dev/badge/skills/alessiomarcone/agent-fieldbook/prompt.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 | $0.00062 | $0.00595 |
| Opus 5 | $0.00031 | $0.00298 |
| Sonnet 5 | $0.00012 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
prompt 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 12d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt
Turn a rough request into the shortest prompt that reliably defines the work.
References
- Read
references/ai-fluency-4d-corso.mdfor Anthropic's Description framework and prompting techniques. - Read
references/codex-prompting.mdfor current Codex prompting rules when the target is Codex. - Read
references/regole-distillate.mdonly for cross-cutting boundaries and verification.
Procedure
- Resolve the target product only when product behavior changes the prompt.
- Recover only missing parts that materially affect the result and are supported by the user's request or supplied context:
- Goal: the result to create or change.
- Context: relevant sources, files, examples, errors, and prior decisions.
- Boundaries: what must stay unchanged, what not to invent, and which actions require approval.
- Output: artifact, format, audience, length, and destination.
- Done when: observable acceptance checks.
- Add examples, role, decomposition, a checklist, or an explicit planning step only when the user requests them or they resolve a concrete ambiguity. Do not add a conventional template merely because it is common for that task type.
- Never invent missing scope, numbers, timelines, audiences, deliverables, or acceptance criteria. Preserve a concise request and its approximate length when the user asks for brevity. Use a visible placeholder for a necessary unknown; ask one focused question only when no useful prompt can be produced without the answer.
- Add a freshness or source requirement for time-sensitive claims.
- Return one ready-to-copy prompt; do not execute it unless requested.
Output contract
Return:
- Ready prompt — one copyable block.
- Assumptions — only unavoidable assumptions; omit if none.
- Why it works — at most two lines.
- Verification — the most important check on the result.
When the user explicitly requests a short or simple rewrite, return only the Ready prompt and, if essential, one line of Verification. Do not append a rationale, assumptions section, or follow-up question.
What ships with it
5 files 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.
- 12d ago First seen · 51 lines · 62 tokens per session scan A 9742833d6466
prompt is a skill published in the GitHub repository alessiomarcone/agent-fieldbook (5 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 595 once invoked, about $0.0003 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 skills, from other repositories
ai-teacher
A guide to teaching about artificial intelligence, including how large language models work, prompt writing, AI agents, tools, and AI ethics.
partner-anthropic
Anthropic intelligence — Claude model family, Claude Code, MCP protocol, Claude for Work programs, May 2026 state, Frank's relationship state, integration patterns. Use when generating Anthropic content, writing about Claude/MCP/Claude Code, partnership-conversation prep for Anthropic, or evaluating new Anthropic…
prompt-hub
Compose the 13-agent Prompt Hub team via @prompt-conductor. Use when designing prompts, optimizing prompts, evaluating prompts, importing patterns from Fabric / awesome-chatgpt-prompts / awesome-claude-prompts, running IFS introspection or psychometric profiling, or building knowledge-base prompt sets. Auto-trigger on…
agent-orchestration-improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
outlines
Outlines: structured JSON/regex/Pydantic LLM generation.
guidance
Constrain LLM output with grammars; guarantee valid JSON.