implement

A task-execution skill carries out a software change only after a plan has been approved.

In plain words
What is it for?
It runs planned coding tasks from a separate Git worktree, or allows a quick fix when the quickfix option is used.
Why use it?
It adds a check that prevents implementation from starting without an agreed plan and guards against making changes in the main code checkout.

Skill for Claude CodeCodex

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 skills/firatcand/forge/implement
Any agent
npx skills add firatcand/forge --skill implement
Clone the repo
git clone --depth 1 https://github.com/firatcand/forge

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 634 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 $0.00025 $0.00634
Opus 5 $0.00013 $0.00317
Sonnet 5 $0.00005 $0.00127
Haiku 4.5 $0.00003 $0.00063

Measured 2d ago against content hash c1ead9ba057d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

skills/implement/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/implement

Preflight: worktree guard

Task-scoped mutating skill — must run from a worktree, not the main checkout. Contract: skills/_shared/worktree-guard.md.

TOPLEVEL="$(git rev-parse --show-toplevel 2>/dev/null || echo '')"
if [ -z "$TOPLEVEL" ]; then
  echo "✗ worktree-guard: not inside a git repository" >&2
  exit 1
fi
BRANCH="$(git branch --show-current 2>/dev/null || echo '')"
DEFAULT_BRANCH="$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null | sed 's@^origin/@@' || echo 'main')"
if [ -f "$TOPLEVEL/.forge/worktree-task.json" ]; then
  echo "✓ worktree-guard: $TOPLEVEL ($BRANCH)"
elif [ "$BRANCH" = "${DEFAULT_BRANCH:-main}" ]; then
  echo "✗ worktree-guard: refusing to run on default branch '$BRANCH' from $TOPLEVEL" >&2
  echo "  Parallel Claude Code sessions on the main checkout clobber each other's HEAD." >&2
  echo "  → cd into an existing worktree, or run /pickup-task to create one." >&2
  exit 1
else
  echo "⚠ worktree-guard: no .forge/worktree-task.json at $TOPLEVEL (branch: $BRANCH)" >&2
  echo "  Proceeding, but this worktree may be manually-created or stale." >&2
fi

Preconditions

  • plans/tasks/{LINEAR-ID}.plan.md exists and was committed
  • OR --quickfix flag with justification

Execution

  1. Read plan
  2. Execute step-by-step, committing after each logical unit
  3. Use conventional commit messages
  4. Mid-implementation forks: If a decision surfaces that wasn't in the plan, apply the fork severity filter from /plan-task (architectural / blast radius ≥ module / medium-high reversibility / changes next 3+ steps). If it qualifies, STOP and emit AskUserQuestion following skills/_shared/question-format.md. Do not auto-pick and document later — the user must see the fork before the code lands.
  5. Record each surfaced question and its answer in the commit message body (single line: Decision: <fork> → <choice> per user answer) so the trail is visible in git history, not just the conversation.
  6. Run npm run typecheck (or equivalent) after each major change

Read the full file on GitHub · 51 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 · 51 lines · 25 tokens per session scan A c1ead9ba057d

Subscribe to this mod's changes

implement is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 634 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 2026-08-30.