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 skills add leifericf/agentic-sdk --skill plan-workgit clone --depth 1 https://github.com/leifericf/agentic-sdkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/leifericf/agentic-sdk/plan-work)<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/plan-work"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/plan-work/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/plan-work"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/plan-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00032 | $0.02386 |
| Opus 5.5 | $0.00013 | $0.00954 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 1mo ago), licensed MIT. It adds 32 tokens to every session and 2,386 once invoked, about $0.0001 per session on Opus 5.5. 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
synergy-tracker
Manage cross-project synergy tracking between sibling projects. Use when the user wants to log a shared pattern, a divergence, an extraction candidate, or something a sibling project has that this one doesn't. Also use when the user wants to promote synergy entries to Basic Memory (workflow 5). NOT for upstream…
upstream-tracker
Manage upstream issue tracking for this project. Use when the user wants to log a bug or friction point in a vendor package or npm dependency, review open upstream items, resolve a tracked issue, run a trend review, generate the upstream observations section of a sprint retrospective, promote upstream observations to…
backlog-groomer
Manage the beads backlog for this project. Use when the user wants to review or triage open issues, reprioritize the backlog, identify obsolete issues to close, investigate a topic to inform future work, create new issues from research findings, or enrich an existing issue with external context. Trigger phrases…
retrospective
Run a sprint retrospective for this project. Use when the user says 'retrospective', 'retro', 'close out the sprint', 'what went well', 'generate retro', or wants to generate a RETRO-NN.md file. Reads UPSTREAM-.md files, recent git history, and conversation context to pre-populate the retrospective. Do NOT use for…
swarm-wave
Orchestrate multi-agent development sprints with wave-based parallelism. Use when the user wants to plan a swarm sprint, partition work into file-disjoint waves, map file contention across open issues, run a post-wave quality gate with review agents, manage agent backpressure, run a parallel research wave, or…
harden-memories
Audit the bd remember store and recommend which entries to prune, so each one earns its per-session bd prime injection cost. Read-only: it proposes a triage table plus the exact bd forget / migration commands; you run them. Use when bd remember entries have accumulated, feel stale, redundant, or conflicting, or when…