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.
npx skills add odarino/haren --skill implementgit clone --depth 1 https://github.com/odarino/harenWrote 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.
[](https://agentmods.dev/skills/odarino/haren/implement)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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)
- Run read-context skill to orient
- Read tasks from the active plan path (see skill.md Plan Paths convention)
- Read
progress.jsonto find current feature status - Read
artifacts/05-implementation/{module}/task-{N}-{slug}.mdif it exists for the target feature (previous session context) - If iterations enabled, also read the master plan path for broader module context if needed
- Pick the highest-priority feature in "pending" status
- Set up the module branch. Follow skill.md "Repos and Git":
- Read the module's repos from the
repos:front matter ofartifacts/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'sdefault_branch, or from the current branch ifdefault_branchis not set. Then switch to it - Record
branchandreposfor the module inprogress.jsonvia update-tracking skill - If the module status is
planned, set it toimplementingvia update-tracking skill
- Read the module's repos from the
Implementation Loop
For each feature:
- Update feature status to "in-progress" via update-tracking skill
- 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
- After implementation:
- (a) Commit the code in each repo that the feature changed:
git -C <repo> commitwith 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.jsonlastCommit.<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.jsonandevents/events.jsonl) in the haren repo. List the code commits in the message, for exampledocs(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
- (a) Commit the code in each repo that the feature changed:
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.
- 15d ago Changed · +10 lines adcb6b844a2a
- 1mo ago First seen · 69 lines · 12 tokens per session scan A 32ff064d6138
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.
Other skills, from other repositories
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.