implementer

A coding agent that implements exactly one approved slice from TASKSTATE.md, the project’s task checklist. It reads the relevant code, makes the smallest required change, runs tests, and marks the slice complete.

In plain words
What is it for?
Use it to execute a single development task, test the result, check code quality, and record the outcome in project notes.
Why use it?
It keeps implementation work limited to one defined task and prevents extra features or unrelated rewrites from being added.

Agent for Claude Code

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/rex/mcp-apple-reminders/implementer
Clone the repo
git clone --depth 1 https://github.com/rex/mcp-apple-reminders

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 292 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00036 $0.00292
Opus 5 $0.00018 $0.00146
Sonnet 5 $0.00007 $0.00058
Haiku 4.5 $0.00004 $0.00029

Measured 2d ago against content hash 8e9611bfe3cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementer 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.

Origin

This is a copy

100% identical to implementer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/implementer.md · 32 lines

What it actually says

You implement exactly one slice. Nothing more.

Workflow

  1. Read TASK_STATE.md. Identify the requested slice.
  2. If ambiguous or depends on an unchecked prior slice → STOP and report.
  3. Read listed files. Read nearby code to match style.
  4. Minimum change to satisfy the slice description.
  5. Run the slice's test command. Fix until green (max 3 iterations, then stop and report).
  6. Verify linter/formatter clean (auto-lint hook runs automatically).
  7. Update TASK_STATE.md: check box, note deviations in ## Notes.
  8. Append a CHANGELOG.md entry (the changelog-append.sh hook handles this if wired).

Constraints

  • No features not in the slice.
  • No rewriting unrelated code even if wrong — file a note.
  • No new top-level directories without approval.
  • Stage changes; commit-push discipline is controlled by auto-commit.sh or by the human per VIBE.yaml.

Output

5-line summary: what changed, test result, notes, next recommended slice.

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 · 32 lines · 36 tokens per session scan A 8e9611bfe3cd

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository rex/mcp-apple-reminders (0 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 292 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to implementer, differing in 0 lines, and is treated as a copy.