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 onboardgit 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/onboard)<a href="https://agentmods.dev/skills/odarino/haren/onboard"><img src="https://agentmods.dev/badge/skills/odarino/haren/onboard/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/onboard"><img src="https://agentmods.dev/badge/skills/odarino/haren/onboard.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 | $0.00063 | $0.01440 |
| Opus 5.5 | $0.00025 | $0.00576 |
| Sonnet 5.5 | $0.00013 | $0.00288 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
haren-onboard 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 7d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Haren Onboard
Run this skill after haren init sets up the workspace. This skill reads and reports. It writes only the manifest fields that the user approves. It never clones, pulls, stashes, switches branches or writes code.
0. Find the haren folder
- The haren folder is the folder whose
manifest.yamlhas a top-levelharen:key. Look in the current folder first, then in its direct child folders. - If no folder has this key, stop. Tell the user to run
haren init. - Read
manifest.yaml,progress.jsonand the "Repos and Git" section ofskill.mdin the haren folder. Follow that section for all repo paths and git commands.
1. Analyze repos
Do these steps for each entry in repos:
- Find the repo folder:
<haren folder>/<path>. If the folder does not exist, skip this repo. Step 2 reports it. - Read the build files that exist in the repo folder:
package.jsonand its lock file,go.mod,pom.xml,build.gradleorbuild.gradle.kts,pyproject.toml,requirements.txt,Cargo.toml,composer.json,Gemfile,*.csproj. - Decide these values:
stack: a short kebab-case name, for examplenode-express,react-vite,nextjs,go,java-spring,python-fastapi.test_cmd: the command that runs the tests, from the package scripts or the build tool, for examplebun test,pnpm test,go test ./...,mvn test,pytest. If you are not sure, leave it empty.default_branch: rungit -C <repo> symbolic-ref --short refs/remotes/origin/HEADand remove theorigin/prefix. If the command fails, use the current branch (see the detached HEAD rule below). Use "main" only if no branch can be found, and say so in the table.role:frontendfor a UI app (React, Vue, Angular, Svelte, Next.js, Nuxt, a Vite web app).backendfor an API or a service.e2efor a repo that holds mainly end-to-end tests.otherfor all other repos. Keep an existingrole. If it looks wrong, ask the user.- Current branch: run
git -C <repo> branch --show-current. If it prints nothing, the repo is on a detached HEAD. Report "detached HEAD at " and get the sha withgit -C <repo> rev-parse --short HEAD.
- Show one table to the user: repo, stack, test_cmd, default_branch, role. Mark the values that change.
- Ask: "Write these values into manifest.yaml?"
- Write only after the user agrees. Change only these fields of the
reposentries. Write them in this order:path,remote,default_branch,role,stack,test_cmd. Keep every other line and every comment inmanifest.yaml.
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.
- 7d ago First seen · 94 lines · 63 tokens per session scan A e069a4a7eea9
haren-onboard is a skill published in the GitHub repository odarino/haren (11 stars, last pushed 7d ago), licensed MIT. It adds 63 tokens to every session and 1,440 once invoked, about $0.0003 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 2026-10-11.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…