cf-implement

A graph-aware implementation command that uses ContextForge’s code knowledge graph to guide changes instead of starting with broad file searches.

In plain words
What is it for?
Use it to load a feature’s context, trace related functions, implement tasks, validate the changed paths, find similar or dead code, update the task list, and report token savings.
Why use it?
It helps an agent understand a feature’s related code and likely impact before editing, while encouraging small changes and checks for unused or duplicated code.

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/capatinore/contextforge-mcp/cf-implement
Clone the repo
git clone --depth 1 https://github.com/capatinore/contextforge-mcp
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 261 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 $0.00000 $0.00261
Opus 5 $0.00000 $0.00130
Sonnet 5 $0.00000 $0.00052
Haiku 4.5 $0.00000 $0.00026

Measured yesterday against content hash 722c8a653e50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cf-implement 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.

contextforge-mcp-v2/contextforge-mcp/extensions/speckit/commands/cf-implement.md · 42 lines

What it actually says

/speckit.cf-implement

Graph-aware implementation. Uses ContextForge instead of file reads.

Arguments

  • $FEATURE_ID — feature directory under specs/
  • $TASK_ID — (optional) specific task number

Steps

Phase 0 — Load context

cf_implement_context(feature_id="$FEATURE_ID")

Phase 1 — Understand the task

For each task, query the graph:

cbm_search_graph(name_pattern="<function from task>")
cbm_trace_path(function_name="<target>", direction="inbound")
cbm_get_impact(node_id="<node>")

Only read the actual file when you need to edit it.

Phase 2 — Implement

  • Make minimum change that satisfies the task
  • Mark task complete in tasks.md
  • Check cbm_find_similar_code before writing new functions

Phase 3 — Validate

cbm_trace_path(function_name="<modified>", direction="both")
cbm_find_dead_code(confidence="high")

Phase 4 — Report

  • Mark task complete
  • cf_stats() — show token savings
  • State next task

Rule: never grep. Always use cbm_* for discovery.

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 · 42 lines · 0 tokens per session scan A 722c8a653e50

Subscribe to this mod's changes

cf-implement is a command published in the GitHub repository capatinore/contextforge-mcp (4 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 261 tokens. 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.