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-featurenpx skills add leifericf/agentic-sdk --skill plan-featuregit 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 | $0.00019 | $0.01005 |
| Opus 5 | $0.00010 | $0.00502 |
| Sonnet 5 | $0.00004 | $0.00201 |
| Haiku 4.5 | $0.00002 | $0.00101 |
Grade A, and why
plan-feature 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-feature
Turn a selected backlog item into a dependency-ordered plan with a Gherkin acceptance gate and parallel quality-dimension assessments. Two modes: plan (default) and review (revise an existing plan).
Procedure
- Read
product-backlog.md,product-requirements.md,decision-log.md, andopen-questions.md. In review mode, read the existing~/.agentic-sdk/<project>/artifacts/planning/tasks/plan-<slug>.mdinstead and treat its Functional Snapshot and Gherkin as source of truth. Surface and resolve any[Blocking]item affecting this feature first. - Functional elicitation gate. Read the backlog item and relevant
requirements; fold in resolved open-question answers. If requirements are
missing or ambiguous, ask in this order, at most two batches of three
questions: problem and intent; success criteria (observable); user outcomes
(must do, must never happen, edge cases); user flow (primary, alternate,
friction); business and domain rules; integrations and their failure
behavior; prioritization (MVI, what is deferred); constraints (privacy,
security, compliance, operational); delight and quality bar. Do not proceed
until you can answer in plain language: the primary user and goal,
observable success, the primary flow, what must never happen, the key edge
cases, the business rules, the integrations and their failure behavior, the
MVI, and what is deferred. If any blocker remains, add a
[Blocking]open question and returnblocked. - Write the Gherkin specification. Treat it as source of truth for
feature-level acceptance: business language and user-observable outcomes,
not UI mechanics. Three to seven scenarios for the MVI, deterministic, each
asserting externally visible state. Include at least one happy path, one
must-never-happen, one key edge case, and one integration or
dependency-failure scenario where applicable. Use
Feature:with a short narrative,Background:only for truly shared preconditions,Rule:to group business rules, andScenario Outline:withExamples:for permutations. - Fan out the four planning dimensions: dispatch assess-observability,
assess-testing, assess-data, and assess-rollout in parallel (module-batch
fan-out; if your context has no sub-agent tool, run them inline per
orchestration.md). Collect each one-line EDN assessment. - Plan chunks and tasks. Decompose into two to six independently testable
chunks that each deliver user value and reduce risk; plan the next chunk in
full and keep later chunks lighter. Write tasks commit-per-task, each leaf
completable in one commit. Capture unrelated later ideas under
Inbox (untriaged)inproduct-backlog.md; do not expand scope unless the user changes the definition of done. Keep the plan a forward-only DAG: security and verification ride with each chunk, not bolted on at the end. - Write the plan to
~/.agentic-sdk/<project>/artifacts/planning/tasks/plan-<feature_slug>.md, filling the section skeleton inplan-template.md. Fold the four dimension assessments into their sections (Observability, Testing Strategy, Data and Migrations, Rollout and Verify); surface anyN/Awith its reason. Follow the project descriptor's VCS and commit form, not any retired commit mechanics in the skeleton. - Review mode. Over an existing plan, surface the gaps that cause rework: success criteria that are not observable, flow ambiguity, missing must-never-happen outcomes, unstated edge cases, ambiguous rules, unspecified integration failure behavior, and an unclear split between the MVI and the deferred scope. Ask the smallest set of clarifying questions, at most two batches of three, in the elicitation order above; prefer plain language and choice questions. Revise the Functional Snapshot, Gherkin, chunks, and tasks, and write the plan back.
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.
- 2d ago First seen · 79 lines · 19 tokens per session scan A d825250ec513
plan-feature is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 19 tokens to every session and 1,005 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
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.