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/ahmadulhoq/agentskel/task-completionnpx skills add ahmadulhoq/agentskel --skill task-completiongit clone --depth 1 https://github.com/ahmadulhoq/agentskelWhat 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 | $0.01642 |
| Opus 5 | $0.00028 | $0.00821 |
| Sonnet 5 | $0.00011 | $0.00328 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
task-completion 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Completion Checklist
A task is NOT complete until every applicable item below is done. Execute this immediately after the last implementation step — before responding to the user or starting anything else.
Step 0 — Applicability Gate
- Run
git status --porcelainin the repo root. - If the only changed paths are inside
.memory/, or there are no changes at all → STOP. This is not a development task (pure discussion, read-only analysis, memory-only maintenance). Do not run the steps below. Respond to the user directly. - Exception: if a workflow invoked this skill explicitly (e.g.
publish-adrorpublish-postmortemafter a Confluence publish with no local file changes) — proceed through every step regardless. The workflow knows it did real work.
Step 1 — CHANGELOG
- Add an entry to
.memory/CHANGELOG.mddescribing what changed and why. - Skeleton repos only: if the change touches any workflow or skill file,
append
affected: name, name, ...at the end of the entry (bothCHANGELOG.mdand.memory/CHANGELOG.md). Omit if no workflow/skill changed. Seereferences/skeleton-contribution-checklist.mdfor the full rule. - Skip only if zero files were modified (e.g. pure analysis tasks).
Step 2 — SYMBOLS / MAP
- If any class or function was created, renamed, or deleted →
update the relevant symbol file. Split mode: update
symbols/[module].mdand the SYMBOLS.md index counts. Single-file mode: update the module section in SYMBOLS.md. - If a module was added or architecture changed → update
.memory/MAP.md. - Skip only if no structural changes were made.
Step 3 — TIME_LOG
- If this was a development task (feature, tech debt fix, hotfix), record it in
.memory/TIME_LOG.mdwith:- Task ID (ticket ID or DEBT-ID)
- Date
- Estimated human hours (from the plan)
- Agent start and end time
- Agent duration
- Files changed (count and list)
- Status (completed / partial / blocked)
- This step is mandatory for all development tasks. Not optional.
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.
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 · 133 lines · 55 tokens per session scan A c76ac23db692
task-completion is a skill published in the GitHub repository ahmadulhoq/agentskel (13 stars, last pushed 16d ago), licensed MIT. It adds 55 tokens to every session and 1,642 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 2026-09-02.
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…