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_explainnpx skills add theafh/ai-modules --skill task_explaingit 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 | $0.00082 | $0.01499 |
| Opus 5 | $0.00041 | $0.00749 |
| Sonnet 5 | $0.00016 | $0.00300 |
| Haiku 4.5 | $0.00008 | $0.00150 |
Grade A, and why
task_explain 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
task_explain
<task_explain_skill>
<when_to_activate> Activate when the user wants an explanation of exactly one task:
- "Explain this task."
- "What is this task about?"
- "Give me a high-level / compact description of this task."
- "What's the goal / why / how of
<task>?" - "Summarize this task."
- "Walk me through
<task>."
Route to task_check when the user asks whether the task is ready to build. Route to task_select when the user asks what to work on next. Route to task_audit when the user asks whether completed work is genuinely done. Route to the base task skill, task_create, task_auto_check, task_implement, task_finish, or task_fix when the user asks for edits, status changes, implementation, close-out, or tree repair.
</when_to_activate>
<discover>- locate the projecttasks/directory.<file_format>- interpret task filenames, frontmatter, statuses, live-vs-archived location, and body sections.<body>- read Goal, Context, Approach, and Acceptance as the source material for the explanation.
Keep shared file-format and backlog-management rules in the base skill. This skill adds only the read-only explanation contract.
<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>
<target_resolution>
Resolve exactly one task file before explaining it. Accept an explicit path, an exact filename or stem, a partial name, an H1 title, or "this task" from the current conversation context. Match across both live tasks under tasks/*.md and closed tasks under tasks/archive/*.md; explaining an archived task is in scope because orientation applies to closed work too.
When no file matches, report the unresolved reference and ask for a task path or name. When more than one file matches, list the candidate paths with their current status and ask one sharp disambiguating question before explaining. Do not choose among ambiguous candidates silently. </target_resolution>
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 · 90 lines · 82 tokens per session scan A d62b9a3759d1
task_explain is a skill published in the GitHub repository theafh/ai-modules (38 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 1,499 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.