cf-spec

A command that creates a TaskSpec.v1 JSON template for a context-firewall workflow. The template includes placeholders for the task, inputs, questions, risk level, and verification settings.

In plain words
What is it for?
Starting context-firewall tasks with an ID, objective, risk setting, input placeholder, questions, map-reduce processing, and critic review.
Why use it?
It gives a task a standard structure that can be edited before processing large inputs or coordinating multiple agents.

Command

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 commands/lollipopkit/cc-plugins/cf-spec
Clone the repo
git clone --depth 1 https://github.com/lollipopkit/cc-plugins
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 422 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 $0.00018 $0.00422
Opus 5 $0.00009 $0.00211
Sonnet 5 $0.00004 $0.00084
Haiku 4.5 $0.00002 $0.00042

Measured 2d ago against content hash d2155740fc8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cf-spec 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 2d 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.

plugins/context-firewall/commands/cf-spec.md · 55 lines

What it actually says

Generate a TaskSpec.v1 JSON template for the user to edit.

Arguments

$ARGUMENTS

Steps

  1. Parse arguments:
  • --id <task_id> (optional)
  • --risk low|medium|high (optional, default: medium)
  • --objective <text> (optional)
  1. Determine task_id:
  • If --id is provided, use it.
  • Otherwise generate one using Bash:
    • date +%Y%m%d for the date
    • uuidgen | tr -d '-' | cut -c1-6 for a short suffix
    • Format: cf-<YYYYMMDD>-<suffix>
  1. Determine risk_level:
  • Use --risk if provided, else "medium".
  1. Determine objective:
  • If --objective is provided, use it.
  • Otherwise set a generic placeholder string that the user should replace.
  1. Output TaskSpec JSON with:
  • version: "TaskSpec.v1"
  • output_schema: "SubResult.v1"
  • map_reduce.enabled: true
  • critic.enabled: true
  • constraints filled with defaults
  • Include minimal schema-valid placeholders:
    • inputs: include a single placeholder input (e.g. { "type": "file", "path": "<PATH>" }).
    • questions: include a single placeholder question (e.g. "<QUESTION>").

Output rules (MANDATORY)

  • Output strict JSON only.
  • Do not use markdown fences.
  • Do not include any explanation text before or after the JSON.
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. 2d ago First seen · 55 lines · 18 tokens per session scan A d2155740fc8d

Subscribe to this mod's changes

cf-spec is a command published in the GitHub repository lollipopkit/cc-plugins (7 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 422 once invoked, about $0.0001 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.