os-task-prep

A skill that turns open software issues into detailed tasks that coding agents can implement without constant supervision. It checks each issue against the actual repository and adds the findings to the issue.

In plain words
What is it for?
Use it to find ready-to-code issues, diagnose them in a local checkout, map dependencies, enrich issue descriptions, optionally assign issues, and create prompts for the implementation workflow.
Why use it?
It removes the guesswork before implementation by documenting the cause, relevant files, dependencies, blockers, acceptance conditions, and verification steps.

Skill for Claude CodeCodex

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 skills/open-software-network/os-clovy/os-task-prep
Any agent
npx skills add open-software-network/os-clovy --skill os-task-prep
Clone the repo
git clone --depth 1 https://github.com/open-software-network/os-clovy

Made for: Claude Code, Codex.

Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,979 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00130 $0.01979
Opus 5 $0.00065 $0.00989
Sonnet 5 $0.00026 $0.00396
Haiku 4.5 $0.00013 $0.00198

Measured 3d ago against content hash c2a63b444c75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

os-task-prep scanned grade A with 1 finding 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/enrich_issue.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Sets `User-Agent: os-platform-agent-skill/1.0` -- the default urllib UA is
.agents/skills/os-task-prep/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

os-task-prep

Productizes the loop: find open Issues -> diagnose against the code -> map cross-Issue dependencies and blockers -> enrich the Issue on the platform -> (optionally) assign -> emit repo-build-pr prompts so autonomous ("AFK") agents can pick them up with full context.

It composes two existing skills and adds the one capability they lack:

  • os-platform (read-only + issues take): list/show Issues, and assign.
  • repo-build-pr: the per-Issue implementation loop the emitted prompts target. Invoke it directly (/repo-build-pr); the old /build alias is deprecated -- do not emit it.
  • scripts/enrich_issue.py (this skill): the only mutation os-platform does not provide -- PATCH /v1/orgs/{org}/bounties/{number} to append diagnosis notes to body_markdown, idempotently and append-only.

Prerequisites

  • OS_PLATFORM_API_KEY must be set in the environment (see the os-platform skill). Never ask the user to paste it into chat; never echo it.
  • Run from a checkout of open-software-network/os-clovy so the diagnosis step can read the real code.
  • The default org/project come from os-platform.json (org, limit).

Workflow

1. Find ready-to-code Issues

Use the os-platform skill. Default to the narrowest actionable queue:

python3 .claude/skills/os-platform/scripts/os_platform.py issues list <org> --status todo --limit 30

Pick candidates that are genuinely ready to code, not just status: todo:

  • Prefer creator.kind: "integration" / well-specified reports with clear expected behavior over raw creator.kind: "user" reports that need triage.
  • Prefer tight, self-contained scope. Flag overlap: Issues that touch the same large file (e.g. AgentWorkspace.tsx) will conflict if run in parallel worktrees -- note which to serialize.
  • Skip design-only / question / vague Issues unless asked.
  • Honor assignment hints: surface unassigned or already-yours first.

State how many you selected and why; log anything you dropped.

Read the full file on GitHub · 170 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 170 lines · 130 tokens per session scan A c2a63b444c75

Subscribe to this mod's changes

os-task-prep is a skill published in the GitHub repository open-software-network/os-clovy (357 stars, last pushed 9d ago), licensed MIT. It adds 130 tokens to every session and 1,979 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

macparakeet-stt

Use when the user asks to transcribe audio or video, inspect or manage MacParakeet meeting recordings, search prior dictations/transcripts, or give an AI agent local speech-to-text tools on Apple Silicon.

moona3k/macparakeet · 50 tokens

verify-dictation

The canonical "prove VZT Flow actually works" checklist — the human hotkey test plus its automated equivalents. Use before claiming a dictation-pipeline change works, before a release, or when the user runs /verify-dictation.

vonzelle-vzt/vzt-flow · 53 tokens

release-murmur

Cut a signed, notarized macOS release of Murmur (Tauri 2 + Angular 22). The exact, proven step-by-step runbook — preflight gates → version bump (+ Cargo.lock sync) → QueaT commit → PR-merge to the murmur trunk (never direct-push) → rustup targets → stop dev → universal build → Developer-ID sign BY IDENTITY HASH (the…

murmur-io/murmur · 168 tokens

ship-feature

Ship a Murmur feature through scope, isolated implementation, fresh adversarial and required security review, project gates, a QueaT commit, and a PR to murmur. Use the verifier-only Harness for risky, multi-step, or explicitly requested work; ordinary low-risk fixes keep the normal isolated-worktree route.

murmur-io/murmur · 68 tokens

dreaming

Tryb kreatywnego śnienia o Murmurze — Codex nasiąka apką, wędruje po necie, kombinuje i WYMYŚLA co możemy dodać, nie jako suchy research tylko swobodne myślenie generatywne oparte o głębokie zrozumienie apki i o to, co akurat przyjdzie do głowy. Rozchodzi się szeroko (dużo dzikich pomysłów), skupia na iskrach, buduje…

murmur-io/murmur · 184 tokens

retrieval-memory-brain

The MAP of Murmur's shipped retrieval + agent-memory stack by file:symbol (hybrid fusion, FTS5/vec0 schema, embedding models, the reranker seam, bitemporal facts, consolidation, the entity graph, the eval harness) plus the MEASURED gaps and the load-bearing invariants. Use for any task touching retrieval quality…

murmur-io/murmur · 117 tokens