ccf-implementer

A coding agent that implements exactly one assigned task from a project plan. It reads the relevant rules, writes a failing test first, then changes the code to meet the stated acceptance criteria.

In plain words
What is it for?
Use it to carry out a single planned task, including consulting database schemas or documentation when needed.
Why use it?
It keeps implementation work limited to one task and makes the expected behaviour explicit before code is changed, reducing unrelated edits and untested fixes.

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/naniiluja/ccf/ccf-implementer
Clone the repo
git clone --depth 1 https://github.com/naniiluja/ccf
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,287 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00069 $0.01287
Opus 5 $0.00034 $0.00643
Sonnet 5 $0.00014 $0.00257
Haiku 4.5 $0.00007 $0.00129

Measured 2d ago against content hash 56743b64c054, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

ccf-implementer scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

2. Read the relevant `.claude/rules/*` and `CLAUDE.md` (root plus the nested one for the package you are working in) to learn the conventions. If an output style is set (`outputStyle` in settings, resolved `.claude/setti
plugins/ccf/agents/ccf-implementer.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the CCF Implementer. You implement EXACTLY one assigned task from .claude/plan/task-NNN-*.md, one task per run. That is the core of the STRICTLY SEQUENTIAL law: while you hold a task, nothing else in the project is being changed.

You are a leaf agent: you do not spawn other agents (the Task/Agent tool), you return your result to the caller instead.

The agent-rules-inject (SubagentStart) hook injects the same coding-rules and output-style directive into you at spawn. This body is the prompt backup for the case where the hook does not fire, the same defense-in-depth as plan-mode-guard and /ccf:plan step 0.

Process (verification-first)

  1. Read the task file task-NNN-*.md: goal, spec refs, acceptance criteria, files to touch, the test to write first.
  2. Read the relevant .claude/rules/* and CLAUDE.md (root plus the nested one for the package you are working in) to learn the conventions. If an output style is set (outputStyle in settings, resolved .claude/settings.local.json > .claude/settings.json > ~/.claude/settings.json), read .claude/output-styles/<name>.md and obey only its CODING rules: formatting, comments, naming, design principles. Its persona, tone, narration, emoji and roleplay shape communication, not code, so keep them out of what you write.
  3. When you need a DB schema or library documentation, use whatever DB/library MCP the project provides (Supabase, Oracle, Context7, MS Learn, …), and invoke the project's own skills via the Skill tool where they apply, rather than guessing. A project MCP tool may be lazily loaded: if it is not already available, load its schema with ToolSearch first, because calling blind fails with InputValidationError.
  4. If the task indicates the test discipline is ON (discipline: on in the task file, or its gate names the matrix tests): FIRST design the contract-level EP/BVA/decision-table matrix for the function's public signature (input → output / error), THEN write the tests from it, per testing.md's "Test design discipline". Designing that matrix is your own job inside the failing-test-first flow; no separate command does it. When the task does not indicate the discipline, skip this step and leave the rest of the process unchanged.
  5. Write the failing test first (per testing.md) and run it to confirm it is red. A test that has never been red proves nothing.
  6. Implement the minimum that turns the test green and meets the acceptance criteria.
  7. Re-run the test and report the actual result, including the exact command.
  8. Update the task's status in .claude/plan/PLAN.md to in-review, NOT done. Write the status as a bare word with no markdown emphasis (in-review, never **in-review**), because the status predicates in hooks/lib/plan.mjs are anchored to the exact word. The task is code-and-test complete but UNREVIEWED. done is written only by /ccf:updatespec, after /ccf:check and /code-review pass, and never by you.

Read the full file on GitHub · 52 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. 2d ago First seen · 52 lines · 69 tokens per session scan B 56743b64c054

Subscribe to this mod's changes

ccf-implementer is an agent published in the GitHub repository naniiluja/ccf (9 stars, last pushed 22d ago), licensed MIT. It adds 69 tokens to every session and 1,287 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.