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 attilaszasz/sdd-pilot --skill clarification-strategiesgit clone --depth 1 https://github.com/attilaszasz/sdd-pilotWrote 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/attilaszasz/sdd-pilot/clarification-strategies)<a href="https://agentmods.dev/skills/attilaszasz/sdd-pilot/clarification-strategies"><img src="https://agentmods.dev/badge/skills/attilaszasz/sdd-pilot/clarification-strategies/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/attilaszasz/sdd-pilot/clarification-strategies"><img src="https://agentmods.dev/badge/skills/attilaszasz/sdd-pilot/clarification-strategies.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 Output Handling · line 23 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00033 | $0.01125 |
| Opus 5 | $0.00016 | $0.00562 |
| Sonnet 5 | $0.00007 | $0.00225 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
clarification-strategies 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 9d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clarification Strategies
Ambiguity Audit Patterns
Patterns to identify weak requirements in spec.md:
1. The "Adverb Trap"
Pattern: "quickly", "easily", "efficiently", "seamlessly". Critique: "Define 'quickly'. <200ms? <1s? Define 'easily'. How many clicks?" Goal: Convert subjective adverbs to measurable metrics.
2. The Passive Voice
Pattern: "The user is notified..." / "The data is processed..." Critique: "WHO notifies? Email? SMS? Toast? WHAT processes? Background job? Synchronous call?" Goal: Identify specific actor and mechanism.
3. The "Unspecified Scale"
Pattern: "Handle user uploads" without size limits. Critique: "Max file size? Allowed types? Expected concurrency?" Goal: Define boundary constraints for Plan phase.
4. The "Missing Failure Mode"
Pattern: "User logs in successfully." Critique: "Wrong password? Locked account? DB down?" Goal: Ensure error paths defined in User Scenarios.
5. The "Scope Creep" Detector
Pattern: "Integration with 3rd party providers" (plural) when one suffices for MVP. Critique: "Which specific providers for V1? Can we limit to one?" Goal: Narrow scope, reduce complexity.
Questioning Protocol
When generating questions:
- Group by Impact: Security > Scope > UX > Technical.
- Propose a Default: "Should we default to JWT for auth, or do you have a specific requirement?"
- Limit Volume: Max 8 critical questions at a time.
- Reference Lines: Point to specific line in
spec.mdwhere ambiguity exists.
Adversarial Stress-Test Patterns
Patterns to detect internal contradictions and constraint violations in resolved specs. Run after collaborative ambiguity questions are answered — the goal shifts from "what did you mean?" to "what breaks if you meant exactly that?"
1. Cross-Requirement Contradiction
Signal: Two requirement or success-criteria IDs impose mutually exclusive constraints.
Heuristic: Pair-wise comparison of quantified constraints across all FR-###, TR-###, OR-###, SC-### entries — flag pairs whose stated bounds conflict at any scale within the spec's defined scope.
Example: "FR-002 mandates real-time sync, but TR-001 caps round-trip latency at 50 ms — under a 10,000-item payload, one of these must yield. Which one relaxes, and under what threshold?"
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.
- 9d ago First seen · 76 lines · 33 tokens per session scan A 6583e55e6155
clarification-strategies is a skill published in the GitHub repository attilaszasz/sdd-pilot (96 stars, last pushed 7d ago), licensed MIT. It adds 33 tokens to every session and 1,125 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
universal-live-check
Universal live-check framework for coding agents. Executes incremental, deterministic validation across all software domains (CLI, backend, frontend, mobile, embedded, libs). Change-type-aware (feat, fix, hotfix, refactor, migrate, docs). Triggers whenever an agent needs to validate code quality, run linting, perform…
spec-driven-task-decomposer
Use this skill when approved requirements and design need to be decomposed into tasks.md for Phase 3 of a Spec-Driven change. It creates atomic, traceable implementation and testing tasks, validates the plan, and should not be used to design architecture or write implementation code.
property-based-testing
Writes, reviews, and debugs property-based tests — Hypothesis, fast-check, proptest, jqwik, rapid, and Echidna or Medusa for Solidity invariants. Use whenever tests should cover a whole input domain instead of a hand-picked list of examples: encode/decode and serialize/deserialize pairs, parsers, canonicalizers and…
mutation-testing
Configures mewt or muton mutation testing campaigns — scopes targets, tunes timeouts, and optimizes long-running runs. Use when the user mentions mewt, muton, mutation testing, or wants to configure or optimize a mutation testing campaign.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.