fpf-work-guide

fpf-work-guide is an agent for Claude Code from ansea09/agent-skills-and-protocols. It costs 32 tokens per session (315 once invoked), scanned A, original, MIT.

A work guide for helping Claude Code plan, reason about, review, and analyze technical tasks using a defined reasoning framework. FPF refers to that framework and its supporting protocols.

In plain words
What is it for?
Use it for planning, architecture analysis, source-sensitive answers, reviews, and other tasks that require protocol-guided reasoning.
Why use it?
It provides a repeatable process for complex work where assumptions, evidence, architecture, or review quality matter.

Agent for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions Claude Code.

Good fit Use it for planning, architecture analysis, source-sensitive answers, reviews, and other tasks that require protocol-guided reasoning.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ansea09/agent-skills-and-protocols/fpf-work-guide
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ansea09/agent-skills-and-protocols

Made for: Claude Code.

Wrote 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.

agentmods badge for fpf-work-guide

README.md
[![agentmods](https://agentmods.dev/badge/agents/ansea09/agent-skills-and-protocols/fpf-work-guide/github.svg)](https://agentmods.dev/agents/ansea09/agent-skills-and-protocols/fpf-work-guide)
Your own site
<a href="https://agentmods.dev/agents/ansea09/agent-skills-and-protocols/fpf-work-guide"><img src="https://agentmods.dev/badge/agents/ansea09/agent-skills-and-protocols/fpf-work-guide/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.

agentmods 80×15 button for fpf-work-guide

Your own site · 80×15
<a href="https://agentmods.dev/agents/ansea09/agent-skills-and-protocols/fpf-work-guide"><img src="https://agentmods.dev/badge/agents/ansea09/agent-skills-and-protocols/fpf-work-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00315
Opus 5 $0.00016 $0.00158
Sonnet 5 $0.00006 $0.00063
Haiku 4.5 $0.00003 $0.00032

Measured 9d ago against content hash 1c1504f43a5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fpf-work-guide 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 9d 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.

claude-code/fpf-work-guide/agents/fpf-work-guide.md · 31 lines

What it actually says

You help Claude Code use the FPF Work Guide skill.

If a SessionStart hook already ran the gate, its output is in context — reuse it instead of re-running. Otherwise, before substantive FPF-backed work, run the refresh gate from the installed skill:

FPF_WORK_GUIDE_SKILL_DIR="${FPF_WORK_GUIDE_SKILL_DIR:-$HOME/.claude/skills/fpf-work-guide}" \
FPF_CACHE_HOME="${FPF_CACHE_HOME:-$HOME/.cache/fpf-work-guide}" \
FPF_UPDATE_STATE_DIR="${FPF_UPDATE_STATE_DIR:-$HOME/.local/state/fpf-work-guide}" \
bash "$FPF_WORK_GUIDE_SKILL_DIR/scripts/update_fpf_context.sh"

Read the gate output before using FPF or protocol sources.

Rules:

  • If the gate reports cached status, call it current cached copy, not latest.
  • If the gate reports blocked status, explain the blocker and ask only for the action needed to restore a valid cache or allow a fetch.
  • If the task is substantive, use the protocol registry reported by FPF_PROTOCOLS_REGISTRY_PATH before selecting a baseline protocol.
  • Do not treat local cache, state, logs, or personal launchers as public skill source.
Changes

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.

  1. 9d ago First seen · 31 lines · 32 tokens per session scan A 1c1504f43a5c

Subscribe to this mod's changes

fpf-work-guide is an agent published in the GitHub repository ansea09/agent-skills-and-protocols (2 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 315 once invoked, about $0.0002 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.