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/codagent-ai/agent-skills/plan-tasksnpx skills add Codagent-AI/agent-skills --skill plan-tasksgit clone --depth 1 https://github.com/Codagent-AI/agent-skillsWhat 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 | $0.00045 | $0.01131 |
| Opus 5 | $0.00023 | $0.00566 |
| Sonnet 5 | $0.00009 | $0.00226 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
plan-tasks 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 3d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Tasks
Create a small set of self-contained delivery tasks from the proposal, specifications, design, any supplied test plan, and relevant repository context. Each task goes to a skilled agent with no prior conversation; include necessary decisions, paths, constraints, scenarios, and automated-test obligations without dictating line-by-line implementation.
Read the proposal, design, specifications, and relevant repository context. When test-plan.md exists
or the caller supplies a test plan, read it and include its obligations; otherwise plan from the
available definition artifacts without requiring or inventing test-plan content.
Size before decomposing
Estimate the whole change from novelty, uncertainty, architectural reach, migration risk, integration breadth, and verification burden. Do not equate file, requirement, scenario, provider, or UI counts with task count.
| LOE | Typical tasks |
|---|---|
| Small | 1 |
| Medium | 2 |
| Large | 3–4, preferably 3 |
| XL | 5+, starting at 5 |
Choose the smallest fitting band. Mechanical propagation across layers or adapters usually remains one task. For Medium-or-larger changes, or unclear provider, migration, cutover, feasibility, or cleanup boundaries, read references/task-sizing.md.
Form delivery units
A task is an independently meaningful outcome a generalist can implement, test, and review in one focused session. Prefer vertical slices that include their schema, config, logic, interfaces, tests, and documentation.
Split only for a distinct outcome, implementation risk, real dependency or release gate, or substantial independently verifiable foundation. Merge boundaries that create broad unfinished plumbing, duplicate edits, or a large implicit handoff. Fold ordinary scaffolding, migrations, refactors, test setup, and documentation into the outcome they support.
When a test plan is supplied, assign each INT-* and E2E-* obligation to the task that first makes
its boundary or journey executable; a cross-task E2E belongs to the final task completing that journey.
Do not assign AT-* or HT-* execution to implementors. Unit cases remain implementation-time TDD
decisions.
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.
- 3d ago First seen · 123 lines · 45 tokens per session scan A 7ee2708797a2
plan-tasks is a skill published in the GitHub repository Codagent-AI/agent-skills (30 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,131 once invoked, about $0.0002 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.
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…