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/theafh/ai-modules/task_selectnpx skills add theafh/ai-modules --skill task_selectgit clone --depth 1 https://github.com/theafh/ai-modulesWhat 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 | $0.00055 | $0.02356 |
| Opus 5 | $0.00028 | $0.01178 |
| Sonnet 5 | $0.00011 | $0.00471 |
| Haiku 4.5 | $0.00006 | $0.00236 |
Grade A, and why
task_select 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 2d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
task_select
<task_select_skill>
<when_to_activate> Activate when the user wants backlog selection or prioritization:
- "What task should I work on next?" / "pick the next task" / "choose from the backlog."
- "Rank my open tasks" / "prioritize tasks in this scope."
- "Which task should I check, implement, or refine next?"
Route elsewhere when the user wants to create a task (task_create or the base task skill), judge one named task's readiness (task_check), automatically repair one task until it is ready (task_auto_check), implement one chosen task (task_implement), verify a completed task (task_audit), close a task (task_finish), repair the tree (task_fix), or list/query tasks without a recommendation (the base task skill).
</when_to_activate>
<path_resolution>
The base task skill's discover_tasks.sh ships in scripts/ next to that skill's SKILL.md, not next to this one. After reading the base SKILL.md (per <authority>), resolve the script's absolute path by combining the directory you loaded it from with scripts/discover_tasks.sh and invoke that absolute path. If the first invocation reports a missing file, re-resolve the absolute path once before treating the script as failed.
</path_resolution>
<candidate_policy>
Eligible candidates are live task files under tasks/*.md whose frontmatter status is open, checked, or ready. Exclude every file under tasks/archive/. Exclude live files whose status is implemented or audited, because their next step is verification or close-out rather than selection for upcoming work.
When the user narrows the scope, filter the eligible set before ranking. Support all of these narrowing forms:
- Scope-group language, such as "task tasks", "api tasks", or "the wiki backlog".
- Filename prefixes or stems, such as
task-skill_,api_, ortasks/api_rate-limit.md. - Frontmatter
scopematches, including path prefixes and quoted labels. - Explicit task names or paths.
When no eligible task remains after discovery or filtering, report the no-candidate state plainly and stop. Do not recommend archived, implemented, or audited work as a fallback candidate. </candidate_policy>
<scoring_criteria> Use the candidate's full task body as the evidence base before scoring it. Read every candidate in full; do not rank from filenames, status, age, or one-line descriptions alone.
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.
- 2d ago First seen · 129 lines · 55 tokens per session scan A bc5a47f63e5b
task_select is a skill published in the GitHub repository theafh/ai-modules (38 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 2,356 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.