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 sow-draftgit 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/sow-draft)<a href="https://agentmods.dev/skills/stanislavnianko/product-discovery-claude-skills/sow-draft"><img src="https://agentmods.dev/badge/skills/stanislavnianko/product-discovery-claude-skills/sow-draft/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/sow-draft"><img src="https://agentmods.dev/badge/skills/stanislavnianko/product-discovery-claude-skills/sow-draft.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 | $0.00066 | $0.01200 |
| Opus 5 | $0.00033 | $0.00600 |
| Sonnet 5 | $0.00013 | $0.00240 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
sow-draft 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SoW Draft
Part of the discovery-phase skill pack ·
deliverablesgroup · readsdiscovery-context.md(runprofile-builderfirst if missing).
Statement of Work draft for the legal team to harden. The discovery team's job is to capture commercial reality precisely; legal then translates to enforceable terms.
This skill produces a draft, not a contract. Always route through agency legal + client legal before signing. The discovery team should not be the last line of defense on contract terms.
Step 1 — Read context + prerequisites
Read discovery-context.md (sections 3. Engagement → Budget context — drives payment structure; 6. Constraints — regulatory clauses), scope-doc.md (deliverables + exclusions), and estimation.md (pricing structure). Recommended: proposal.md (consistency with what's already shared with client) and risk-assumption-map.md (informs warranty language).
If discovery-context.md is missing, ask the BA inline: "(a) budget structure (fixed-fee / T&M / milestone-based); (b) regulatory constraints (GDPR / HIPAA / SOC2 / none)?" — tag the output [ASSUMED COMMERCIAL] and DRAFT-ONLY. If scope-doc.md or estimation.md is missing, ask for stand-in bullets, or proceed with [TBD] placeholders and a non-removable DRAFT-ONLY banner — NOT for legal review until placeholders resolved. Never block; recommend profile-builder / feature-scoping / estimation for high-stakes work.
Step 2 — Fill the template
Fill ./template.md. It owns the structure (parties, deliverables table, out-of-scope, timeline + milestones, pricing model, payment terms, change-requests, acceptance + revisions, warranties, IP + confidentiality, termination, client dependencies, assumptions, outsourcing-specific clauses, signatures). This skill's job is the content; the template is the shape.
Fields that hide disputes — be precise here:
- Acceptance criteria (per deliverable). "User can complete X workflow without errors" not "system works". Vague = future dispute.
- Out of scope. Verbatim from
scope-doc.md"out" + "explicitly deferred". Critical — prevents post-signature scope creep. - Pricing model. Pick from
discovery-context.mdbudget context: fixed-fee (tight scope, repeat work) / T&M with cap (moderate uncertainty) / pure T&M (staff aug, exploratory) / phased (long engagement with gates). Spell out: rates per discipline if T&M, fixed numbers if fixed-fee, milestone amounts if phased. - Change-request process. Without it, every "small addition" mid-build becomes an argument. Specify: who can request, how submitted, estimation turnaround (3-5 business days typical), sign-off authority, how changes affect price + timeline.
- Warranties. What the agency warrants (e.g., 30-60 day bug-fix window post-delivery) AND what's NOT warranted (third-party issues, scope changes, environment). Bound from
risk-assumption-map.md[agency]rows. - Client dependencies. From
scope-doc.mdoutsourcing extras + risk-map[client]rows. State explicitly that delays may impact timeline + cost. Don't bury — top-section visible. - Assumptions. Verbatim from
estimation.md"Assumptions that invalidate the estimate". If any becomes false, SoW is voidable / must be amended.
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 · 68 lines · 66 tokens per session scan A 307a335194ab
sow-draft is a skill published in the GitHub repository stanislavnianko/product-discovery-claude-skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 1,200 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.
subcontract-writer
Generate a complete subcontract from a firm's template, awarded bid, and project specs. Outputs a Word document. Triggers: 'subcontract', 'sub agreement', 'write contract', 'draft subcontract'. Requires awarded bid.
code-researcher
Scope-specific code gap analysis — extracts referenced codes from project docs, researches what should apply, surfaces the delta. Triggers: 'code research', 'what codes apply', 'code check', 'ADA requirements', 'egress'.
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…