agentmods.dev

RIPDPI: Skill for Claude Code

.agents/skills/repo-task-board/SKILL.md

repo-task-board is a skill for Claude Code, Codex from po4yka/RIPDPI. It costs 48 tokens per session (394 once invoked), scanned A, original, BSD-3-Clause.

A repository task-board workflow for creating, tracking, validating, executing, and closing project work. It uses task files and OpenSpec files as the source of truth, while generating a board view.

In plain words
What is it for?
Use it to inspect ready work, create and transition tasks, validate task data, generate the board, and close completed or dropped work.
Why use it?
It keeps task state, dependencies, work locations, and completion records consistent instead of relying on hand-edited board files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is po4yka/RIPDPI's own configuration. It tells Claude Code and Codex how to work on RIPDPI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RIPDPI configures →

not rated 85repo yesterday A scan 48 tokens original BSD-3-Clause
View source ↗ po4yka/RIPDPI
Reuse

Borrowing it

Nothing to install: this file belongs to po4yka/RIPDPI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/po4yka/RIPDPI/main/.agents/skills/repo-task-board/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/po4yka/RIPDPI

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 repo-task-board

README.md
[![agentmods](https://agentmods.dev/badge/skills/po4yka/ripdpi/repo-task-board/github.svg)](https://agentmods.dev/skills/po4yka/ripdpi/repo-task-board)
Your own site
<a href="https://agentmods.dev/skills/po4yka/ripdpi/repo-task-board"><img src="https://agentmods.dev/badge/skills/po4yka/ripdpi/repo-task-board/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 repo-task-board

Your own site · 80×15
<a href="https://agentmods.dev/skills/po4yka/ripdpi/repo-task-board"><img src="https://agentmods.dev/badge/skills/po4yka/ripdpi/repo-task-board.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 394 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 $0.00048 $0.00394
Opus 5.5 $0.00019 $0.00158
Sonnet 5.5 $0.00010 $0.00079
Haiku 4.5 $0.00005 $0.00039

Measured yesterday against content hash d8f6402ace83, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

repo-task-board 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.

.agents/skills/repo-task-board/SKILL.md · 24 lines

What it actually says

Repository task board

docs/tasks/issues/*.md is the portfolio source of truth. docs/tasks/board.md is generated. Execution lives in exactly one of:

  • simple work: docs/tasks/work/<TASK-ID>.md;
  • specification-driven work: openspec/changes/<change>/tasks.md.

Use only ./taskctl for lifecycle operations:

  • inspect: list, show, ready, graph;
  • create/start/update: new, start, transition, steps;
  • validate: verify, validate, generate-board;
  • complete: openspec archive, then close prepare --outcome done, commit, and later close purge in a separate commit;
  • drop: close prepare --outcome dropped, commit its receipts, then openspec archive and close purge before the deletion commit.

Stable IDs are area-prefixed with globally unique 16-digit numeric suffixes. Worktrees share a locked allocator reservation through the Git common directory; committed validation catches cross-clone collisions. blocked_by is canonical; reverse blocks is derived. See docs/tasks/README.md's "OpenSpec decision" section for the exact spec_mode: required criteria -- do not re-derive or paraphrase that list here. Never hand-edit the generated board, use direct upstream archive, pass --no-validate, close work without evidence, or delete a record before its terminal-state commit exists.

Before parallel agents write, record ownership and serialized shared-file lanes in the portfolio task. All implementation work uses a dedicated worktree and follows AGENTS.md.

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 · 24 lines · 48 tokens per session scan A d8f6402ace83

Subscribe to this mod's changes

repo-task-board is a skill published in the GitHub repository po4yka/RIPDPI (85 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 48 tokens to every session and 394 once invoked, about $0.0002 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 2026-11-07.

Project managementandroidandroid-vpnanti-censorshipcensorship-circumventiondeep-packet-inspectiondns-over-https
Related

repo-task-board compared with skills from other repositories

repo-task-board next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
repo-task-boardpo4yka/RIPDPISkill85yesterdayBSD-3-ClauseA48Claude Code, Codex
cindy-plugin-creatormakecindy/cindySkill9.5ktodayApache-2.0A48Codex
argent-react-native-app-workflowsoftware-mansion/argentSkill3.2ktodayApache-2.0A46Claude Code, Codex
engineer-bot-opsmakecindy/cindySkill9.5ktodayApache-2.0A57Claude Code, Codex
apple-search-ads-review-evidencemakecindy/cindySkill9.5ktodayApache-2.0A59Claude Code, Codex
seo-aeo-desk-evidencemakecindy/cindySkill9.5ktodayApache-2.0A43Claude Code, Codex
argent-tv-interactsoftware-mansion/argentSkill3.2ktodayApache-2.0A107Claude Code, Codex