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-systemnpx skills add leifericf/agentic-sdk --skill plan-systemgit 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 | $0.00015 | $0.00840 |
| Opus 5 | $0.00008 | $0.00420 |
| Sonnet 5 | $0.00003 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
plan-system 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-system
Role: the upstream planning cycle. Takes a problem or idea to an approved backlog and feature plan, ready to hand to advance-plan or implement-change.
Prerequisites
~/.agentic-sdk/<project>/project.edn exists (run bootstrap-project first).
~/.agentic-sdk/<project>/artifacts/ is scaffolded: project-meta, the decisions log, and
open-questions.
Procedure
- Describe the problem. Dispatch describe-problem to elicit the
problem, stakeholders, constraints, and success criteria. It writes
planning/problem-description.mdand parks unresolved items inopen-questions.md. Hold its one-line return. - Define requirements. Dispatch define-requirements against the
problem statement. It writes
planning/product-requirements.mdwith testable functional and non-functional requirements. Resolve any blocking open question before continuing. - Review risks. Dispatch review-risks against the requirements and
problem statement. It surfaces contradictions, risky assumptions, and
missing acceptance criteria, and writes
planning/risk-assumption-review.md. - Design the UX, when the descriptor sets
:ui? true. Dispatch design-ux. It writesplanning/ux-design-guide.md. Skip when the project has no UI surface; the rest of the cycle does not depend on it. - Design the technical solution. Dispatch design-technical against
the requirements, risk review, and UX guide (when present). It
writes
planning/technical-design.mdagainst the project's architecture pattern (Functional Core / Imperative Shell by default) and active languages, and records any real choice via record-decision. - Create the backlog. Dispatch create-backlog from the requirements,
risk review, UX guide (when present), and technical design. It
writes
planning/product-backlog.mdin four buckets: Now/Next, Later, Inbox, In product. - Pick and plan the first feature. Dispatch pick-feature against
the backlog, then plan-feature on the picked item. plan-feature runs
the functional elicitation gate (problem, success, flows,
must-never-happen, edge cases, the minimal viable increment),
writes the Gherkin acceptance spec, fans out the assess-* concerns
(assess-observability, assess-testing, assess-data, assess-rollout)
in parallel, and writes the feature plan to
planning/tasks/plan-<feature>.md. The Gherkin gate is folded into plan-feature; plan-system does not run it as a separate step. - Present the gate. Show the maintainer: the backlog, the picked feature, and the feature plan summary. The plan plus the backlog is the one approval gate. On approval, hand the feature plan to advance-plan (several slices) or implement-change (one slice).
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 · 76 lines · 15 tokens per session scan A b6d4e1e0f7d3
plan-system is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 15 tokens to every session and 840 once invoked, about $0.0001 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.
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…