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 stanislavnianko/product-discovery-claude-skills --skill proposalgit clone --depth 1 https://github.com/stanislavnianko/product-discovery-claude-skillsWrote 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/stanislavnianko/product-discovery-claude-skills/proposal)<a href="https://agentmods.dev/skills/stanislavnianko/product-discovery-claude-skills/proposal"><img src="https://agentmods.dev/badge/skills/stanislavnianko/product-discovery-claude-skills/proposal/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/stanislavnianko/product-discovery-claude-skills/proposal"><img src="https://agentmods.dev/badge/skills/stanislavnianko/product-discovery-claude-skills/proposal.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 | $0.00064 | $0.01435 |
| Opus 5 | $0.00032 | $0.00718 |
| Sonnet 5 | $0.00013 | $0.00287 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
proposal 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 12d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proposal
Part of the discovery-phase skill pack ·
deliverablesgroup · readsdiscovery-context.md(runprofile-builderfirst if missing).
Agency-to-client proposal document. The output the client reads, signs (or doesn't), and budgets against.
Step 1 — Read context + prerequisites
Read discovery-context.md (sections 3. Engagement → Mode — if mode is staff aug or internal, suggest discovery-handoff instead, but allow override; 5. Expected deliverable).
Prerequisite artifacts — the proposal's substance:
scope-doc.md— scope languageestimation.md— effort + assumption listrisk-assumption-map.md— risk register- Recommended:
problem-canvas.md,opportunity-tree.md
If discovery-context.md is missing, ask the BA inline: "(a) engagement mode (pre-sale / paid discovery / other); (b) client name + sector?" — tag [ASSUMED]. If 1–2 prerequisite artifacts are missing, ask for 3–5 stand-in bullets per artifact. If 3+ are missing, strongly recommend running the prerequisite skills first; otherwise proceed with [ASSUMED <artifact>] placeholders and a non-removable DRAFT-ONLY banner at the top of proposal.md (NOT for client send). Never block.
Step 2 — Pick proposal style
| Style | When | Length |
|---|---|---|
| Executive brief | Senior client decision-maker, pre-sale, time-pressured | 2-3 pages |
| Detailed proposal | Procurement / RFP response, larger engagement | 8-12 pages |
| Pitch deck | Initial conversation; supplements verbal pitch | Doc + companion deck |
Default to executive brief unless context section 3 (Mode) implies RFP.
Step 3 — Required sections (in this order)
- Cover — engagement title, client name, agency name, date, version, primary contact
- TL;DR — 3-4 bullets max. The client should be able to forward just this.
- Problem we'd solve — one paragraph from
problem-canvas.md, in client-language. NOT in agency-language. - What we learned (if discovery happened already) — 3-5 bullets from
insight-matrix.mdtop-3 with one quote each. Supports the recommendation. - Recommended approach — what we'd build, why this and not alternatives. Pull from
opportunity-tree.mdchosen-direction. If client pre-proposed a different solution and our recommendation differs, handle this section carefully — see step 4. - Scope — pull "in" column from
scope-doc.md. Include the success metrics. - Out of scope — pull "out" column + "explicitly deferred". Crucial — prevents post-contract scope wars.
- Approach / phases — high-level timeline aligned to discipline matrix from
estimation.md. Show milestones, not all tasks. - Team — who from agency works on what. Pull discipline columns from estimation.
- Timeline — calendar weeks, key milestones, decision points
- Effort and pricing guidance — from
estimation.mdadjusted total. Range, not a number. Specify whether fixed-fee, T&M, or phased. - What we need from you — the client-side assumptions and dependencies (from
scope-doc.mdoutsourcing extras +risk-assumption-map.md[client]/[shared]rows) - Risks and how we'll handle them — from
risk-assumption-map.mdregister, prioritized - Assumptions — verbatim from
estimation.md"Assumptions that invalidate the estimate" - Next steps — concrete, signable: "we'll send a SoW within 5 business days of your verbal yes" or similar
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.
- 12d ago First seen · 92 lines · 64 tokens per session scan A 6556565720e7
proposal is a skill published in the GitHub repository stanislavnianko/product-discovery-claude-skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 1,435 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
jtbd-extractor
Turn raw research into Jobs-to-be-Done statements showing what users are really trying to accomplish. Use when: extract jobs, jtbd analysis, jobs to be done, what job is the user hiring, underlying user needs.
assumption-mapper
Surfaces the assumptions a product or strategy depends on, classifies them by criticality and evidence quality, and produces a prioritized test plan. Use when: assumption mapping, identify assumptions, what could go wrong, leap-of-faith assumptions, riskiest assumption test, RAT, assumption inventory, validate before…
competitive-analyzer
Structured competitive teardown for product discovery - surface the 4-6 dimensions buyers actually weigh, score every competitor on each, and identify exploitable gaps. Use when: competitive analysis, competitor teardown, market positioning, where do we win, where do we lose, competitive gap analysis, competitor audit.
feedback-prioritizer
Triages a backlog of raw customer feedback into a ranked list of opportunities scored on reach, severity, strategic fit, and confidence. Outputs a prioritized list with explicit "do not act" callouts for vocal-minority signals. Use when: triage feedback, prioritize feature requests, customer feedback backlog, what…
north-star-metric-finder
Identifies a candidate North Star Metric (NSM) for a product - the single metric that captures the value the product delivers to its customers and predicts long-term business growth. Tests candidates against five criteria and surfaces input metrics that move it. Use when: north star metric, NSM, single metric that…
prd-taskmaster
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…