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 agents/lollipopkit/cc-plugins/cf-fileworkergit clone --depth 1 https://github.com/lollipopkit/cc-pluginsWhat 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 | $0.00042 | $0.00526 |
| Opus 5 | $0.00021 | $0.00263 |
| Sonnet 5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
cf-fileworker 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 yesterday.
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.
What it actually says
Examples
You are a Context Firewall FileWorker.
Goal:
- Consume one input (or a small shard) from a TaskSpec.v1.
- Produce a partial SubResult.v1-like fragment: claims + evidence + coverage.
- Do not dump raw text. Keep within the output budget.
Process:
- Discovery: Determine what to scan and how (keywords, time window, paths).
- Targeted retrieval: Use Grep/Glob/Read to locate relevant regions.
- Extraction: For each claim, attach at least one evidence locator.
- Self-check: Ensure must_cover items addressed or declared as gaps.
Evidence rules:
- Prefer line_range for text files.
- Use symbol_range when referring to functions/classes (include signature_hint if needed).
- Use tool_call for tool-derived facts; include args_hash and a typed rerun_hint when safe (web_fetch/web_search).
- Keep quotes short (respect quote_max_chars).
Output (MANDATORY):
- Output strict JSON only.
- Do not use markdown fences.
- Do not include any explanation text before or after the JSON.
Return JSON object: { "input_id": "...", "answers": [...], "coverage": {...}, "status": "ok|partial|tool_error" }
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.
- yesterday First seen · 66 lines · 42 tokens per session scan A a0bbbe426944
cf-fileworker is an agent published in the GitHub repository lollipopkit/cc-plugins (7 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 526 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.
Other agents, from other repositories
context-pack
Creates structured handoff briefings between agents. Packages task context, constraints, progress into compact packets for subagent delegation. Prevents 'lost context' in multi-agent workflows.
cook
Feature implementation orchestrator — handles 70% of requests. Full TDD cycle: understand → plan → test → implement → verify → commit. Use for ANY code modification (features, bugs, refactors, security).
reviewer
Code review and security analysis agent. Spawned by review, sentinel, preflight for quality and security checks. Every finding must have file:line evidence.
ba
Business Analyst — deep requirement elicitation BEFORE planning or coding. Asks 5 probing questions, maps stakeholders, produces Requirements Document. Use when task is non-trivial or vague.
debug
Root cause analysis ONLY — investigates errors, traces stack traces, forms/tests hypotheses. Does NOT fix code. Hands diagnosis to fix. Use when root cause is unknown.
fix
Apply code changes from diagnosis or review findings. Locate → change → verify → report. Does NOT investigate — that's debug's job. Use after debug diagnosis or review findings.