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 owainlewis/blueprint --skill plangit clone --depth 1 https://github.com/owainlewis/blueprintWrote 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/owainlewis/blueprint/plan)<a href="https://agentmods.dev/skills/owainlewis/blueprint/plan"><img src="https://agentmods.dev/badge/skills/owainlewis/blueprint/plan/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/owainlewis/blueprint/plan"><img src="https://agentmods.dev/badge/skills/owainlewis/blueprint/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 89 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00042 | $0.01239 |
| Opus 5.5 | $0.00017 | $0.00496 |
| Sonnet 5.5 | $0.00008 | $0.00248 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
plan 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 6d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan
Create tasks that a new agent can finish without making product or technical decisions. Every task and milestone must be a vertical slice: a usable outcome that runs through the required layers and has acceptance checks. Split by working result, not by file, layer, or team boundary.
Process
- Read the source, repository instructions, and relevant code.
- Stop and return to
/specif an unresolved choice would change behavior, interfaces, data, security, scale, performance, compatibility, operations, cost, or proof. - Split the work into tasks that each deliver working behavior, fit one agent run, and produce one focused pull request.
- Keep shared contracts in one task. Do not make two tasks answer the same question independently.
- Separate refactoring when it would hide a behavior change.
- Order tasks by dependency. Group tasks into milestones when useful. Each milestone delivers a usable end-to-end result, with acceptance checks and dependencies. Do not use milestones such as “database”, “backend”, or “frontend”.
- Return the plan in chat. Create tracker tickets only when the user asks. Never write a plan document.
- Stop after planning. Do not implement.
For example, “add a task and see it after a restart” includes CLI input, validation, storage, output, and tests in one task. A later milestone could deliver “manage unfinished tasks” through add, list, and complete slices. Name the milestone's observable result and how to prove the whole result works.
Write for two readers
Each task is read by a human and executed by an agent.
The first sections must let a human understand the task in under a minute. State the concrete problem, the result, and why it matters in everyday words. Do not use requirement IDs, implementation details, undefined project terms, or acronyms unfamiliar to the intended readers there.
Put task-specific decisions, interfaces, failure rules, and security constraints in Agent notes. Link the spec or decided source for shared architecture and full requirement definitions. Use a repository path or URL that will resolve from the published ticket, and pin the decided version when later edits could change the contract. If no durable source exists, include the required shared decisions in Agent notes. Do not copy the whole source into every ticket.
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.
- 6d ago Changed · +1 lines dc27b2078e58
- 12d ago Changed · +2 lines 2956a9c22705
- 1mo ago First seen · 97 lines · 42 tokens per session scan A 3a30f99f8e1e
plan is a skill published in the GitHub repository owainlewis/blueprint (416 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 1,239 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
speckit-status
Before the first runner call, resolve and keep the caller's working directory per Installed runner transport.
working-days-get-working-days
Calculate the number of working days between two dates, optionally accounting for country-specific holidays.
speckit.backlog
Backlog Manager - Manage Ideas, Pending Requests and scan TODO/FIXME from codebase.
speckit.roadmap
Roadmap Strategist - Maintain evidence-backed milestones, dependencies, risks, and phase transitions.
speckit.status
Progress Dashboard - Calculate phase and task progress from tasks.md with evidence and risk visibility.
speckit.taskstoissues
Issue Tracker Syncer - Convert tasks.md into deterministic, import-ready issue artifacts without remote mutation.