Borrowing it
Nothing to install: this file belongs to aiblueprinthq/ai-blueprint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aiblueprinthq/ai-blueprint/main/.agents/skills/discovery/SKILL.mdgit clone --depth 1 https://github.com/aiblueprinthq/ai-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/aiblueprinthq/ai-blueprint/discovery)<a href="https://agentmods.dev/skills/aiblueprinthq/ai-blueprint/discovery"><img src="https://agentmods.dev/badge/skills/aiblueprinthq/ai-blueprint/discovery/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/aiblueprinthq/ai-blueprint/discovery"><img src="https://agentmods.dev/badge/skills/aiblueprinthq/ai-blueprint/discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 71 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 | $0.00054 | $0.01827 |
| Opus 5.5 | $0.00022 | $0.00731 |
| Sonnet 5.5 | $0.00011 | $0.00365 |
| Haiku 4.5 | $0.00005 | $0.00183 |
Grade A, and why
discovery 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 7d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
discovery - develop the plans through a deep conversation
Context reuse: Reuse any required file already loaded in project instructions or the current session. Read it again only if absent, changed, or exact current bytes or line references are needed.
First action: Before project inspection, preflight, or any other tool call,
publish running to blueprint/.state/run.json when blueprint/.state/
exists. From the project root, run the first helper that exists,
node .agents/skills/blueprint-doctor/scripts/run-state.mjs or
node .claude/skills/blueprint-doctor/scripts/run-state.mjs, with start --command <skill> --summary "<truthful summary>" --boundary <read-only|reviewed|local-only>. Use update at milestones, with --status blocked --resume <command> for a blocker, and finish --status ready|completed
at the end; --help lists every option and blueprint/workflow.md has the full
activity contract. A missing or failing helper is a warning, not a blocker.
Where this can sit in the workflow:
/onboard -> write the plans directly -> /overview
\
-> [discovery] -> review and approve plan drafts -> /overview
/discovery is an optional planning partner, not a required workflow gate and
not a quick questionnaire. It can span as many turns as the project needs. Its
job is to help the user think through the product, preserve the depth and nuance
of that conversation, and draft the two user-owned planning files only when the
user asks for drafts.
Running /onboard never starts this skill. Empty plans never require it. A user
who writes detailed plans manually, has another AI conversation, or arrives with
finished plans continues directly to /overview exactly as before.
For a focused idea or technical tradeoff without drafting plans, use /explore.
Discovery develops the broader product plans.
Step 1 - establish the starting point
Read only the planning and project facts needed for the conversation:
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.
- 7d ago Changed · +7 lines c1cfb57a414c
- 1mo ago Changed · +3 lines 1c01283ec348
- 1mo ago Changed · +4 lines 9a539c7e5a43
- 2mo ago Changed · +2 lines · -65 tokens per session 25b1bd03ffe3
- 2mo ago First seen · 171 lines · 119 tokens per session scan A e009a594eff4
discovery is a skill published in the GitHub repository aiblueprinthq/ai-blueprint (493 stars, last pushed 7d ago), licensed MIT. It adds 54 tokens to every session and 1,827 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.
discovery compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| discoveryaiblueprinthq/ai-blueprint | Skill | 493 | 7d ago | MIT | A | 54 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |