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/fall-out-bug/sdp/discoverynpx skills add fall-out-bug/sdp --skill discoverygit clone --depth 1 https://github.com/fall-out-bug/sdpWhat 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 | $0.00021 | $0.01553 |
| Opus 5 | $0.00010 | $0.00776 |
| Sonnet 5 | $0.00004 | $0.00311 |
| Haiku 4.5 | $0.00002 | $0.00155 |
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 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@discovery - Product Discovery Gate
Validate before specifying. Answer "should we build this?" before "how should we build this?"
EXECUTE THIS NOW
When user invokes @discovery "feature description" or when @feature invokes it (unless --quick):
Phase 1: Roadmap Pre-Check
- Extract 3-5 high-signal keywords from the feature description (nouns + domain verbs — NOT generic terms like "add", "update", "implement").
- If memory search returns > 10 results, reduce to 2 most specific terms.
sdp memory stats # warn if index > 24h old
sdp memory search "<keyword1> <keyword2> <keyword3>"
-
Analyze results for:
- Features in ROADMAP.md covering same domain terms
- Workstream files with matching Scope Files or goals
- Existing docs/drafts/idea-*.md that cover similar territory
-
Present Overlap Report (HIGH and MEDIUM confidence only; log LOW to file):
Found N potentially related items: [HIGH] Rework Loop — covers [summary]. Similarity reason: [1 sentence] [MEDIUM] 00-008-02 — touches [same module]. Overlap type: [data model / API / user flow] -
User resolution (single question):
- A) These are different — proceed to Phase 2
- B) This extends existing workstream — incorporate and modify
- C) This supersedes existing workstream — flag for later review (propose: set status to 'deferred')
- D) Show me more detail before deciding
Gate: Proceed only after user resolves.
Mode --quiet: Phase 1 only, then stop. Output: overlap report only.
Phase 2: Signal Check (~30 seconds)
-
Ask 2 questions:
- "What user problem does this solve and for whom?"
- "Do you know of existing solutions (libraries, tools, competitors)?"
-
Run web search:
"{feature_name} existing solutions 2026" -
Route to track:
| Condition | Track |
|---|---|
| User answers both confidently AND search finds ≥1 clear prior art | OBVIOUS |
| User answers but search shows competitive landscape | COMPETITIVE |
| User uncertain on Q1 OR search shows no clear prior art | NOVEL |
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 · 192 lines · 21 tokens per session scan A 2dde04fecbeb
discovery is a skill published in the GitHub repository fall-out-bug/sdp (19 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 1,553 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 2026-08-30.
Other skills, from other repositories
typescript-best-practices
Enforces TypeScript best practices and modern patterns.
Tech Debt Auditor
Identifies and prioritizes technical debt in a codebase with an effort/impact matrix.
Unit Test Improver
Reviews existing unit tests for gaps, weak assertions, and missing edge cases, then rewrites them to be more robust.
Refactor Planner
Creates a safe, step-by-step plan to refactor messy code without breaking existing behavior.
code-discipline
Coding methodology for production-grade software development. Enforces structured thinking before coding, verifying reality, simplicity, surgical changes, contract awareness, and verifiable success criteria. Use when writing, reviewing, or refactoring code that needs to remain reliable over time, including production…
umbra-trust-review
Verify AI-generated code before shipping. Run Umbra's Trust Score scan before committing or finishing any coding task, treat findings as blocking issues, and re-scan until clean. Use when finishing a task, before a commit, or when reviewing code written by an agent.