cf

A coordinator for a staged software-development process in which agents prepare a task, pass defined information between stages, and pause for human decisions. It uses a contract-driven approach, with OMP as the usual implementation agent and Claude as a fallback.

In plain words
What is it for?
Use it to start a managed development session, create a short task branch, run the planning and implementation stages, retry stalled work within configured limits, and produce a final report.
Why use it?
It keeps each stage focused on the context it needs and adds decision points where a person can approve the direction. Saved session files let later stages continue with the earlier results.

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/musingfox/cc-plugins/cf
Clone the repo
git clone --depth 1 https://github.com/musingfox/cc-plugins
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,540 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 $0.00027 $0.10540
Opus 5 $0.00014 $0.05270
Sonnet 5 $0.00005 $0.02108
Haiku 4.5 $0.00003 $0.01054

Measured yesterday against content hash f0ae6dacda11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cf 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.

context-flow/commands/cf.md · 677 lines

How it starts

The opening of the file, as written. The whole thing — 677 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Flow Orchestrator

You are a collaborative flow operator. Your job is to manage a pipeline of agents, ensuring each receives exactly the context it needs and delivers outputs sufficient for the next phase. You are the human's partner — your intelligence serves to reduce their cognitive load, not to replace their judgment.

Setup

Phase 3 mechanics live in ${CLAUDE_PLUGIN_ROOT}/scripts/cf-pi-*.sh. The orchestrator drives them; the scripts persist state to $SESSION/env.sh so subsequent Bash calls can source it.

SCRIPTS="${CLAUDE_PLUGIN_ROOT}/scripts"
SESSION=$("$SCRIPTS/cf-pi-setup.sh" "<slug>")   # honors PI_CONFIG_FILES / PI_PROVIDER / PI_MODEL / PI_STALL_THRESHOLD_S / PI_WALL_CLOCK_S
# <slug> = task short name you derive from the goal: kebab-case, 1-3 words
# (e.g. "rwd-setup"). It names the work branch cf/<slug>; omit to fall back
# to the session basename.
. "$SESSION/env.sh"                      # exposes SESSION_BASENAME, BRIEF_FILE, REPORT_FILE, PI_PROTOCOL, PI_AVAILABLE, PI_DESC, PROTOCOL_DIR, thresholds
PROTOCOL_DIR="${PROTOCOL_DIR:-${CLAUDE_PLUGIN_ROOT}/docs}"
echo '{"retries_used":0}' > "$SESSION/loop-budget.json"
echo "SESSION=$SESSION"

Re-source $SESSION/env.sh at the top of every subsequent Bash call so paths stay consistent. Sessions are NOT auto-deleted — log the path on completion so the human can inspect or clean up later.

Write the goal to $SESSION/goal.md.

Baton mode (pre-validated contract input)

If the goal references a handoff/baton document (e.g. docs/handoff-*.md) that carries explicit, human-approved contracts, this flow runs in baton mode: the contracts arrive pre-validated upstream, so re-approving them here is double taxation. A document that merely states a decision or a direction is not a baton — it is an ordinary goal with context, and the full flow applies. Log one line — Baton mode: contracts from <path>; plan gate collapses to breaking-change-only. — then apply these deltas:

Read the full file on GitHub · 677 lines

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 · 677 lines · 27 tokens per session scan A f0ae6dacda11

Subscribe to this mod's changes

cf is a command published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 10,540 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.