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 agentmods add skills/xerrors/taskr-skill/taskrnpx skills add xerrors/taskr-skill --skill taskrgit clone --depth 1 https://github.com/xerrors/taskr-skillWhat 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 | $0.00071 | $0.02909 |
| Opus 5 | $0.00036 | $0.01455 |
| Sonnet 5 | $0.00014 | $0.00582 |
| Haiku 4.5 | $0.00007 | $0.00291 |
Grade A, and why
taskr 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.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taskr
Taskr is a repo-local task protocol stored under .taskr/. Use it to keep implementation intent, checklist progress, optional progress notes, verification, and commits in human-readable Markdown.
Installation Policy
Taskr Skill is distributed independently from the @xerrors/taskr npm CLI package. The canonical Skill source lives in this repository at skills/taskr/SKILL.md so standalone skill installers can discover it from the repository root.
Use the open skills installer for new installs:
npx --yes skills add xerrors/taskr-skill --skill taskr --agent claude-code
npx --yes skills add xerrors/taskr-skill --skill taskr --agent codex
npx --yes skills add xerrors/taskr-skill --skill taskr --agent codex --global
Project installs are written into the target repository's agent-specific skill directory. Global installs use the selected agent's user-level skill directory. Use --copy with the skills installer when a real copied file is preferred over a symlink.
Do not recommend npx --yes @xerrors/taskr install-skill ... for new installs. That command is retained only as a deprecated compatibility command that points users to the standalone skills installer.
The Taskr CLI is still distributed through npm. In ordinary target repositories, do not assume the user has installed a global taskr binary or added Taskr as a project dependency. Prefer npx commands for task operations:
npx --yes @xerrors/taskr init
npx --yes @xerrors/taskr list
npx --yes @xerrors/taskr board --open
If npm cannot infer the scoped package binary for Taskr task operations in a particular shell, use the explicit package form:
npx --yes --package @xerrors/taskr taskr list
Use a bare taskr ... command only when the current environment explicitly provides that binary. If npx and the CLI are unavailable, edit .taskr/tasks/<task-id>.md directly according to the format below.
Trigger Policy
- If
.taskr/exists, use Taskr for substantial implementation, fix, refactor, investigation, and planning work in the repo. - If
.taskr/does not exist, initialize it only when the user explicitly mentions Taskr or invokes/taskr. - Do not create a task for trivial edits unless the user asks to track them.
- Prefer reusing a matching
planned,in_progress, orpending_confirmationtask over creating a duplicate. - Do not use
closed; Taskr tracks only planned, in-progress, pending-confirmation, implemented, and blocked work.
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.
- yesterday First seen · 204 lines · 71 tokens per session scan A 02984a1cd752
taskr is a skill published in the GitHub repository xerrors/taskr-skill (10 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 2,909 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…