implement

implement is a skill for Claude Code, Codex from odarino/haren. It costs 12 tokens per session (1,048 once invoked), scanned A, original, MIT.

A workflow for implementing the features in a module’s plan one at a time. It reads the project context and progress files, then guides development, testing, commits, and status updates.

In plain words
What is it for?
Use it to select the next pending feature, implement it with test-driven development, commit the code, record the session, and mark the feature ready for evaluation.
Why use it?
It keeps implementation work aligned with the approved plan and makes each feature’s progress and decisions traceable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: agent in frontmatter; mentions subagents.

Good fit Use it to select the next pending feature, implement it with test-driven development, commit the code, record the session, and mark the feature ready for evaluation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/odarino/haren/implement
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.

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

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for implement

README.md
[![agentmods](https://agentmods.dev/badge/skills/odarino/haren/implement/github.svg)](https://agentmods.dev/skills/odarino/haren/implement)
Your own site
<a href="https://agentmods.dev/skills/odarino/haren/implement"><img src="https://agentmods.dev/badge/skills/odarino/haren/implement/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for implement

Your own site · 80×15
<a href="https://agentmods.dev/skills/odarino/haren/implement"><img src="https://agentmods.dev/badge/skills/odarino/haren/implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,048 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00012 $0.01048
Opus 5.5 $0.00005 $0.00419
Sonnet 5.5 $0.00002 $0.00210
Haiku 4.5 $0.00001 $0.00105

Measured 15d ago against content hash adcb6b844a2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 15d 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.

content/skills/implement/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement

Execute the implementation plan for a module, one feature at a time.

Pre-Implementation (every session)

  1. Run read-context skill to orient
  2. Read tasks from the active plan path (see skill.md Plan Paths convention)
  3. Read progress.json to find current feature status
  4. Read artifacts/05-implementation/{module}/task-{N}-{slug}.md if it exists for the target feature (previous session context)
  5. If iterations enabled, also read the master plan path for broader module context if needed
  6. Pick the highest-priority feature in "pending" status
  7. Set up the module branch. Follow skill.md "Repos and Git":
    • Read the module's repos from the repos: front matter of artifacts/03-modules/{module}/module.md. If it lists no repos, follow "No repos listed" in skill.md "Repos and Git"
    • For each repo: if it has uncommitted changes, stop and ask the user what to do. Changes inside the haren folder do not count as uncommitted changes for this check
    • For each repo: if the branch feat/{module-slug} does not exist, create it from the repo's default_branch, or from the current branch if default_branch is not set. Then switch to it
    • Record branch and repos for the module in progress.json via update-tracking skill
    • If the module status is planned, set it to implementing via update-tracking skill

Implementation Loop

For each feature:

  1. Update feature status to "in-progress" via update-tracking skill
  2. Delegate to superpowers:subagent-driven-development:
    • Pass the full task description from tasks.md
    • Pass the design context from design.md
    • Ensure TDD discipline via superpowers:test-driven-development
  3. After implementation:
    • (a) Commit the code in each repo that the feature changed: git -C <repo> commit with a descriptive message. In the monorepo layout, make one code commit for all repo keys; see skill.md "Repos and Git"
    • (b) Record each new commit SHA in progress.json lastCommit.<repoKey> via update-tracking skill
    • Update feature status to "evaluating" via update-tracking skill
    • Append to task session log (task-{N}-{slug}.md): what was done, decisions made, any deviations from plan, and the commit SHA for each repo
    • Emit "feature-ready" event to events/events.jsonl
    • (c) Commit the haren files (session log, progress.json and events/events.jsonl) in the haren repo. List the code commits in the message, for example docs(checkout): task 2 session log — backend@abc1234, frontend@def5678. In the monorepo layout the haren folder is in the same repo, so (a) and (c) are two commits on the same branch: the code commit first, then the haren commit. In the workspace layout, commit the haren files on the haren repo's current branch. Do not create a module branch in the haren repo.
    • Never push

Read the full file on GitHub · 79 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. 15d ago Changed · +10 lines adcb6b844a2a
  2. 1mo ago First seen · 69 lines · 12 tokens per session scan A 32ff064d6138

Subscribe to this mod's changes

implement is a skill published in the GitHub repository odarino/haren (11 stars, last pushed 7d ago), licensed MIT. It adds 12 tokens to every session and 1,048 once invoked, about $0.0000 per session on Opus 5.5. 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.