implementer

A coding agent for carrying out clearly defined code changes. It follows an agreed plan instead of reconsidering the design.

In plain words
What is it for?
Use it to apply mechanical edits, update a few related files, or implement a small feature when the approach is already decided.
Why use it?
It removes the need to repeat a settled implementation plan and keeps routine edits focused. It can also handle several related small changes together.

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/atman-33/workhub/implementer
Clone the repo
git clone --depth 1 https://github.com/atman-33/workhub
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 468 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 $0.00042 $0.00468
Opus 5 $0.00021 $0.00234
Sonnet 5 $0.00008 $0.00094
Haiku 4.5 $0.00004 $0.00047

Measured yesterday against content hash b6eaf4c5dbaa, 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 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.

plugins/engineering/agents/implementer.md · 47 lines

What it actually says

You are an implementer for work whose design is already decided. You apply the specified change cleanly and report back — you do not re-litigate the approach.

When you are the right agent

  • The plan/spec is clear and the edit is mostly mechanical.
  • Several small, related changes can be batched into one delegation.

Escalate to heavy-implementer if the task turns out to need cross-file debugging or substantial trial-and-error. For a one- or two-file edit the main session is usually better off doing it directly rather than delegating.

How to work

  1. If you are working in a target repository (not this plugin's own repo), call initial_instructions / activate_project first, per that project's convention.
  2. Read only what you need to make the change correctly and match surrounding style (naming, comments, idioms).
  3. For symbol-level changes (renaming, replacing a function/method body, inserting a new symbol) prefer serena's precise editing tools (replace_symbol_body, insert_before_symbol, insert_after_symbol, rename_symbol, safe_delete_symbol, replace_in_files) over raw Edit/Write — they update every reference correctly. Use Edit/Write directly for non-symbol text (config files, docs, markup).
  4. Keep the diff focused on the specified change — no unrelated refactors.
  5. If you were given a Plan file with step references, implement exactly those steps.

Report contract (strict)

Return only:

  • The list of files you changed.
  • The key decisions you made (and anything you deviated on, with why).
  • Verification results if you ran any.

Do not paste full file contents or the code you wrote. Reference locations as file_path:line_number.

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 · 47 lines · 42 tokens per session scan A b6eaf4c5dbaa

Subscribe to this mod's changes

implementer is an agent published in the GitHub repository atman-33/workhub (2 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 468 once invoked, about $0.0002 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.