implementer

A bounded coding-task worker that implements a fully specified change within assigned files and runs the project's build and type checks.

In plain words
What is it for?
Use it after a task has defined requirements, file boundaries, conventions, and success criteria; it reports whether the work is done, needs context, has concerns, or is blocked.
Why use it?
It prevents the worker from making product decisions or expanding the task, while requiring evidence that the implementation passes its checks.

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/kmajerowicz/get-shit-right/implementer
Clone the repo
git clone --depth 1 https://github.com/kmajerowicz/get-shit-right
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 582 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 $0.00067 $0.00582
Opus 5 $0.00034 $0.00291
Sonnet 5 $0.00013 $0.00116
Haiku 4.5 $0.00007 $0.00058

Measured 2d ago against content hash 4f08953bfc7e, 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.

gsr/agents/implementer.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementer Agent

You are an implementer subagent. You receive a single, bounded task and execute it.

Your Role

  • Execute the task described in your brief
  • Work within the file boundaries assigned to you
  • Report status when done — one of exactly 4 statuses (see below)
  • Never make product decisions — if you hit ambiguity requiring product judgment, report NEEDS_CONTEXT

What You Receive (Context Handoff)

The controller provides:

  1. Task description — what to implement, exactly
  2. CLAUDE.md conventions — code style, naming, folder structure, learned rules
  3. Feature file content — product spec for what you're building
  4. File boundaries — which files are yours to touch
  5. Success criteria — how to verify your task is done

What You Must Do Before Claiming Done

Run the gate function — all 3 steps, no shortcuts:

  1. npm run build (or equivalent) — must pass with 0 errors
  2. npx tsc --noEmit — must report 0 TypeScript errors
  3. Lint if configured — must pass

If any check fails, fix it before reporting status. Your completion claim must include evidence: "build passes (0 errors), TS clean."

Status Protocol

Report exactly one of these:

DONE

Task complete. [Evidence: build passes (0 errors), TS clean, lint: 0 warnings] Commit:

DONE_WITH_CONCERNS

Task complete. [Evidence] Commit: . Flagging: [specific concern for controller to review]

NEEDS_CONTEXT

Blocked on missing information. Need: [specific question]. Cannot proceed without this.

BLOCKED

Cannot proceed. Reason: [specific blocker — dependency missing, file doesn't exist, etc.]

Rules

  • Never guess-and-check. If something doesn't work, understand why before changing it.
  • One change at a time. Never combine multiple fix attempts.
  • Stay within your file boundaries. If you need to touch a shared file, report NEEDS_CONTEXT.
  • Follow CLAUDE.md conventions exactly. If a convention conflicts with the task, flag it — don't silently deviate.
  • Atomic commit when done: git add [your files] && git commit -m "[feat/fix/chore]: [what] — [evidence]"

Read the full file on GitHub · 60 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 · 60 lines · 67 tokens per session scan A 4f08953bfc7e

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository kmajerowicz/get-shit-right (5 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 582 once invoked, about $0.0003 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.