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 ntorga/agent-starter-kit --skill plan-managementgit clone --depth 1 https://github.com/ntorga/agent-starter-kitWrote 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/ntorga/agent-starter-kit/plan-management)<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/plan-management"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/plan-management/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/ntorga/agent-starter-kit/plan-management"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/plan-management.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 | $0.00023 | $0.01685 |
| Opus 5 | $0.00012 | $0.00843 |
| Sonnet 5 | $0.00005 | $0.00337 |
| Haiku 4.5 | $0.00002 | $0.00169 |
Grade A, and why
plan-management 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
This skill defines everything about plans: when to grill, how to ground and review the plan artifacts, how to execute epics, and how to revise. Read this skill whenever the task may require a plan.
Procedure
Plans live in a directory under .memory/plan/:
.memory/plan/<feature-slug>/
├── tree.md — the design tree: decisions, dependencies, recommendations, impact
├── plan.md — acceptance criteria, what + why only
├── arch.md — directory structure, layer separation, reference projects
└── impl.md — epics grouped at one day of work, grounded with file paths, method signatures, test specs
<feature-slug>— short kebab-case summary of the feature.tree.md— the grill's working state. The Architect builds and extends it. All nodes settled when the grill terminates.plan.md— acceptance criteria from the settled business decisions. Living document, edited inline as understanding evolves.arch.md— directory structure, layer separation, reference projects. Produced during the grill. The beginner path gets defaults from the maintenance, lightweight, and safe principles (KISS, single responsibility, safe boundaries —rules/code/general.md).impl.md— epics grouped at one day of work. The grill transcribes them. The Architect grounds and re-grounds them. Living document, edited inline as epics land.
Epic completion tracking: Epics in impl.md are annotated with ✓ when fully delivered, or ~ when partially delivered. All epics marked ✓ means the feature is complete.
Parallelizable groups: impl.md notes which epics can run in parallel. The Maestro may dispatch parallel epics to separate coders when file scopes do not overlap (follows: skills/dispatch/SKILL.md).
Deciding When to Plan
A plan is required when the request is lengthy, multi-part, or describes a non-trivial change. When in doubt, plan — planning a simple task wastes minutes; skipping a plan on a complex task wastes hours.
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 · 119 lines · 23 tokens per session scan A 78f013908896
plan-management is a skill published in the GitHub repository ntorga/agent-starter-kit (142 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,685 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 2026-09-13.
Other skills, from other repositories
board
Read and write the workspace BOARD.md (shared task board for agents + Val). Wraps bin/board, a small Python CLI that preserves the markdown schema and appends to the activity log automatically. Use this whenever an agent proposes, claims, or finishes work that should be visible to the rest of the roster.
squads-cli
Squads CLI — operate your AI workforce through the loop; intent in, reviewed work out. TRIGGER when running squads, dispatching agents, triaging the inbox, reading/writing memory, recording feedback, or checking status/usage.
gh
You have access to gh (GitHub CLI) for repository and project management.
pm
Project Manager skill. One orchestrator session drives eight subagent roles -- planner, plan-reviewer, doer, reviewer, deployer, integ-test-runner, ci-watcher, harvester -- through cycles of Plan, Develop, Test, and Harvest across one or more parallel tracks in isolated git worktrees, running each task on a…
auto-sprint-args
How to construct and pass correct arguments to the auto-sprint workflow -- the required issues+branch fields, optional goal/maxcycles/basebranch/requirementsFile, JSON-object (not string) shape, and common launch mistakes. Trigger when preparing to launch or invoke auto-sprint.
fleet-sprint-cli
How to launch and supervise apra-fleet's autonomous sprint workflow from the CLI (apra-fleet workflow fleet-sprint) -- the --issue/--members/--branch/--base flag contract, the preconditions to check first, how to launch it as a detached process, and how to watch it via its dashboard. Trigger before running apra-fleet…