discovery

A product-discovery checkpoint that checks whether a proposed feature fits the roadmap before detailed design begins.

In plain words
What is it for?
Use it to search existing project knowledge, report possible overlap, and prepare a feature brief for the next planning stage.
Why use it?
It helps find overlapping plans, drafts, or workstreams before time is spent specifying the feature.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fall-out-bug/sdp/discovery
Any agent
npx skills add fall-out-bug/sdp --skill discovery
Clone the repo
git clone --depth 1 https://github.com/fall-out-bug/sdp

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,553 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 2dde04fecbeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

prompts/skills/discovery/SKILL.md · 192 lines

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

  1. Extract 3-5 high-signal keywords from the feature description (nouns + domain verbs — NOT generic terms like "add", "update", "implement").
  2. 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>"
  1. 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
  2. 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]
    
  3. 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)

  1. Ask 2 questions:

    • "What user problem does this solve and for whom?"
    • "Do you know of existing solutions (libraries, tools, competitors)?"
  2. Run web search: "{feature_name} existing solutions 2026"

  3. 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

Read the full file on GitHub · 192 lines

Changes

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.

  1. 2d ago First seen · 192 lines · 21 tokens per session scan A 2dde04fecbeb

Subscribe to this mod's changes

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.