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 irahardianto/awesome-agv --skill structured-specgit clone --depth 1 https://github.com/irahardianto/awesome-agvWrote 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/irahardianto/awesome-agv/structured-spec)<a href="https://agentmods.dev/skills/irahardianto/awesome-agv/structured-spec"><img src="https://agentmods.dev/badge/skills/irahardianto/awesome-agv/structured-spec/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/irahardianto/awesome-agv/structured-spec"><img src="https://agentmods.dev/badge/skills/irahardianto/awesome-agv/structured-spec.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 | $0.00140 | $0.02306 |
| Opus 5.5 | $0.00056 | $0.00922 |
| Sonnet 5.5 | $0.00028 | $0.00461 |
| Haiku 4.5 | $0.00014 | $0.00231 |
Grade C, and why
structured-spec scanned grade C with 1 finding 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 1mo 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
6. **`draft` is never blocked.** Enforcement scales with `status`; see `specification.md` §6.3. Do not refuse to write a rough draft because it lacks tests. How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Spec
Specification documents that are readable by humans, writable by agents, and parseable by machines. Standard GitHub-Flavored Markdown plus typed annotations carried in HTML comments, so renderers ignore them and parsers don't have to guess.
Standard version 2.0.0. Every file in this directory is at 2.0.0; do not mix with v1 documents (see specification.md §9 to migrate one).
Use this skill when
- Writing or reviewing a PRD, SDD, implementation plan, TSD, BDD spec, or ADR
- Validating a spec's completeness or requirement traceability
- Migrating plain Markdown into the structured format
- Slicing a spec into work packages for multiple agents
Not for: ordinary prose docs, READMEs, or runbooks that have no requirements to trace.
Where to look
Read only what the task needs. These files do not repeat each other — each fact lives in exactly one place.
| Question | File |
|---|---|
| Which document type do I write? | This file, next section |
| What are the annotation fields and rules? | specification.md §3–§4 |
| How does traceability work? | specification.md §5 |
| When is a spec complete? | specification.md §6 |
Which type value do I use? |
taxonomy.md |
| What section order for this doc type? | profiles/<doc_type>.md |
| Is the frontmatter legal? | spec-schema.json |
| Show me a full real document | example-prd.md |
| Give me a blank starting point | template.md |
| Is this document actually valid? | Manual review against specification.md §6 completeness rules |
Pick the profile
doc_type is a closed set of seven. Choose by the question the document answers:
| The document answers | doc_type |
Profile |
|---|---|---|
| WHY — business context, users, success criteria | prd |
profiles/prd.md |
| HOW — architecture, components, trade-offs | sdd |
profiles/sdd.md |
| WHEN and WHO — tasks, sequencing, owners | implementation-plan |
profiles/implementation-plan.md |
| INTERFACE — APIs, payloads, errors, versioning | tsd |
profiles/tsd.md |
| BEHAVIOR — scenarios and edge cases | bdd |
profiles/bdd.md |
| DECISION — one choice, its alternatives and consequences | adr |
profiles/adr.md |
| None of the above | custom |
no profile; universal rules only |
What ships with it
11 files 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.
- 1mo ago First seen · 183 lines · 140 tokens per session scan C 01c6ad5cfde9
structured-spec is a skill published in the GitHub repository irahardianto/awesome-agv (156 stars, last pushed 9d ago), licensed MIT. It adds 140 tokens to every session and 2,306 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
android-finance-spec
Use when generating, reviewing, or refactoring Android Kotlin code for financial apps that require BigDecimal/String precision, RTL/i18n safety, Kotlin style discipline, and "do not reinvent existing project patterns" constraints.
om-system-extension
Extend installed Open Mercato modules through UMES enrichers, interceptors, mutation guards, widgets, menus, entity extensions, events, component/page replacements, and overrides. Use for "extend core", "add field/column/action", "hide page", "intercept API", "UMES", or "rozszerz moduł".
om-build-workflow
Build or extend standalone business workflows, activities, event triggers, durable user tasks, compensation, output paths, idempotency, and live progress. Use for "add workflow", "custom activity", "CALLAPI", "approval task", "workflow progress", or "zbuduj workflow".
om-evolve-harness
Add a reproducible standalone agent-harness use case or correct failed routing/context with semantic assertions, one knowledge owner, and before/after evaluation. Use for "add harness case", "agent got this wrong", "extend the harness", "new use case", or "rozszerz harness".
om-troubleshooter
Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.
om-trim-unused-modules
Analyze and disable unused built-in modules in a standalone app without breaking dependencies, navigation, backend landing, bootstrap, or generation. Use for "trim classic mode", "remove unused modules", "slim app", "disable built-ins", or "wyłącz moduły".