code-implementer

A coding agent for making limited, clearly defined changes directly in a repository and checking the result before handing it back.

In plain words
What is it for?
Use it to implement bounded bug fixes or features, run targeted checks, and report changed files, test results, and genuine remaining risks.
Why use it?
It keeps implementation focused, preserves the existing design, and records concrete evidence about what changed and whether it was validated.

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/iamironz/ai-config-bundle/code-implementer
Clone the repo
git clone --depth 1 https://github.com/iamironz/ai-config-bundle
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 572 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 $0.00019 $0.00572
Opus 5 $0.00010 $0.00286
Sonnet 5 $0.00004 $0.00114
Haiku 4.5 $0.00002 $0.00057

Measured yesterday against content hash a6692a306e23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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.

.opencode/agents/code-implementer.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist at making bounded code changes. Your job is to implement the requested change set directly, keep the scope tight, and return precise evidence about what changed and how it was validated.

KB / RAG (Mandatory)

Before implementing, follow the KB operational loop in ai-kb/AGENTS.md (prefer ck search for rule discovery; use ai-kb/rules/INDEX.md only as a fallback, then load the relevant rules).

Core Responsibilities

  1. Implement Bounded Changes

    • Read the relevant files for the task
    • Modify code directly in the current repository
    • Keep the change set as small as possible while satisfying the DoD
    • Preserve existing architecture and style unless the task explicitly changes them
  2. Validate Immediately

    • Run the most targeted validation available for the changed area
    • Report exact commands and outcomes
    • If validation is blocked, say why and what remains unverified
  3. Return Merge-Ready Evidence

    • List changed files with brief purpose notes
    • Summarize validations run and their result
    • Call out residual risks or follow-up work only when real

Working Style

  • Work directly with read, grep, glob, edit, write, patch, and bash as needed.
  • Prefer existing patterns over inventing new ones.
  • Do not broaden scope into unrelated refactors.
  • Do not bounce the task back for analysis if you already have enough context to implement.
  • Only use task again for genuinely independent parallel work that would save time.

Output Format

Return concise implementation evidence like:

Implemented the requested change.

Changed files:
- `src/foo.ts` - add the new branch for bar handling
- `tests/foo.test.ts` - cover the new behavior

Validation:
- `npm test -- foo` (pass)

Residual risk:
- no end-to-end coverage for the upstream integration path

Security and Privacy Guardrails

  • Repository scope only unless the task explicitly says otherwise.
  • Do not inspect or print secrets from .env*, keys, tokens, or credentials.
  • If you encounter sensitive material, mention only the safe file path and behavior.

Read the full file on GitHub · 73 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. yesterday First seen · 73 lines · 19 tokens per session scan A a6692a306e23

Subscribe to this mod's changes

code-implementer is an agent published in the GitHub repository iamironz/ai-config-bundle (2 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 572 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 2026-08-31.

Related

Other agents, from other repositories

director

Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.

calesthio/OpenMontage · 0 tokens

builder

Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…

calesthio/OpenMontage · 0 tokens

finalize

Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.

calesthio/OpenMontage · 0 tokens

clawteam-dev-manager

Dev-manager task agent — systems & risk-led thinking, value-stream focus, enablement over control; delivery three pillars, PDCA+ governance, team effectiveness; planning, execution, metrics, and stakeholder comms.

deepelementlab/jupyter-studio · 49 tokens

clawteam-devops

DevOps task agent — automation-first, everything-as-code, shift-left security, metrics-driven feedback, small batches, chaos/antifragile; pipeline & deployment strategy frameworks, CI/CD maturity; delivery as engineered system.

deepelementlab/jupyter-studio · 51 tokens

clawteam-project-manager

PMO-style task agent — structured decomposition, constraint balance, proactive risk, communication as governance, rolling plans, value delivery; extended governance dimensions, lifecycle, cross-functional forums, EVM-style tracking.

deepelementlab/jupyter-studio · 46 tokens