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/leifericf/agentic-sdk/plan-worknpx skills add leifericf/agentic-sdk --skill plan-workgit clone --depth 1 https://github.com/leifericf/agentic-sdkWhat 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 | $0.00032 | $0.02386 |
| Opus 5 | $0.00016 | $0.01193 |
| Sonnet 5 | $0.00006 | $0.00477 |
| Haiku 4.5 | $0.00003 | $0.00239 |
Grade A, and why
plan-work 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-work
Role: the planning specialty advance-plan dispatches before it drives.
Decomposes one chunk of the approved feature plan into a forward-only DAG
of phases and tasks, writes the full plan to the run's plan.edn, and
returns a compact summary. The big plan lives on disk; only the summary
rides back in context. It plans; it does not write source or dispatch
other agents.
Input: a named chunk of the approved feature plan, plus the run slug.
Output: the full plan at ~/.agentic-sdk/<project>/runs/<slug>/plan.edn and a
compact summary returned to the caller.
Stance
Read skills/shared/references/orchestration.md before planning; its
laws bind this work. Four applications matter here:
- Context is the budget. The plan can be large. It goes to
plan.edn, never into the return. The return is the phase list, the task counts, the critical path, and the conflicts, nothing more. A planner that returns the full plan defeats the reason it runs in a sub-agent. - Forward-only: a DAG, not a loop. Decompose into phases and tasks that flow one direction. A phase lands before any phase that depends on it starts. Order to minimise work in progress. Never plan a step that backtracks into landed work to make later work fit; if an earlier decision proves wrong, that is a new forward task, not a rewind.
- Autonomy: decide and record. Where the feature plan leaves a
choice open, pick the recommended option, note the pick in the task's
:descand the plan's:notes, and plan the task to settle it. Do not stall on an open choice; the plan records the decision and moves on. - Shift security and verification left. Each task carries its own
test layers as part of its definition of done. Where a task takes
untrusted input or crosses a native edge between languages, its
:donenamescheck-securityand the relevant verify lanes, not a gate bolted on at the end.
Procedure
- Assess what is landed. Do not trust the feature plan to tell you where the project is; read the ground truth:
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 · 205 lines · 32 tokens per session scan A 09c24c4e9a56
plan-work is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 32 tokens to every session and 2,386 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 2026-08-31.
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.