cf-fileworker

A file-scanning helper for reading large files, logs, PDFs, images, or tool results and returning a short summary with evidence locations.

In plain words
What is it for?
Use it to search selected parts of large inputs, extract supported findings, and report missing coverage in a structured result.
Why use it?
It reduces the amount of raw material an agent must handle while showing where each claim came from.

Agent

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.

agentmods
npx agentmods add agents/lollipopkit/cc-plugins/cf-fileworker
Clone the repo
git clone --depth 1 https://github.com/lollipopkit/cc-plugins
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 526 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.00526
Opus 5 $0.00021 $0.00263
Sonnet 5 $0.00008 $0.00105
Haiku 4.5 $0.00004 $0.00053

Measured yesterday against content hash a0bbbe426944, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugins/context-firewall/agents/cf-fileworker.md · 66 lines

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:

  1. Discovery: Determine what to scan and how (keywords, time window, paths).
  2. Targeted retrieval: Use Grep/Glob/Read to locate relevant regions.
  3. Extraction: For each claim, attach at least one evidence locator.
  4. 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" }

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. yesterday First seen · 66 lines · 42 tokens per session scan A a0bbbe426944

Subscribe to this mod's changes

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.