Borrowing it
Nothing to install: this file belongs to w00fx/spec-anchored-agentic-development. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/w00fx/spec-anchored-agentic-development/main/.agents/skills/to-spec/SKILL.mdgit clone --depth 1 https://github.com/w00fx/spec-anchored-agentic-developmentWrote 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/w00fx/spec-anchored-agentic-development/to-spec)<a href="https://agentmods.dev/skills/w00fx/spec-anchored-agentic-development/to-spec"><img src="https://agentmods.dev/badge/skills/w00fx/spec-anchored-agentic-development/to-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/w00fx/spec-anchored-agentic-development/to-spec"><img src="https://agentmods.dev/badge/skills/w00fx/spec-anchored-agentic-development/to-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 | $0.00101 | $0.00943 |
| Opus 5.5 | $0.00040 | $0.00377 |
| Sonnet 5.5 | $0.00020 | $0.00189 |
| Haiku 4.5 | $0.00010 | $0.00094 |
Grade A, and why
to-spec 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 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.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn the material in this conversation — a shape session is the
common case — into the capability spec. If pointed at notes or a
transcript instead, work from those. This skill does not
interview: the questions already happened. If material for a
template section is missing, list it under Open questions — ask
nothing, invent nothing, default nothing silently.
Write
- Identify the capability (the argument, or the session's subject). Resolve
its one stable logical-contract entrypoint at
specs/<capability>/<capability>.md, usingspec-templates/capability-spec.md. The entrypoint may later declare companion files without creating another authority. - Create mode (no spec exists yet): fill every template section
from the resolved material — Capability language as an opinionated
glossary (canonical term;
_Avoid_:synonyms; what it IS, not what it does); normative behavior in the representation its truth type demands (EARS as the default; decision tables, state models, formulas+oracles, schemas per the template's matrix), each externally-sourced rule with its citation (identifier + version + scope); Acceptance criteria in Given/When/Then, each with its typed stable ID; reference-value rows for every calculation; Non-goals with teeth; Contracts and dependencies. - Update mode (the spec exists): produce the delta — new rules, new items get typed IDs issued in continuation (the ID is the addressing scheme; tickets point at it), new or changed reference rows, non-goal updates. Never renumber or rewrite existing criteria unless the interview explicitly resolved a change to them.
- Large reference tables (beyond a screen) go to
specs/<capability>/tables/as data files the golden tests read; the rule cites the file.
The completeness pass (writer-side — the interrogation was shape's)
Before reporting done:
- Every template section is either filled or explicitly represented in Open questions.
- Oracle coverage: every rule has an executable expression (reference values → golden; GWT → tests) or is explicitly marked human-judgment territory.
- Every externally-sourced rule carries its citation.
- The spec stays layer-agnostic: no deployment targets, no framework names, no file paths — behavior and business truth only (the how lives in plans and ADRs).
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.
- 1mo ago First seen · 80 lines · 101 tokens per session scan A c873acaa7f26
to-spec is a skill published in the GitHub repository w00fx/spec-anchored-agentic-development (7 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 943 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
code-simplifier
Always-active simplicity rules: no speculative abstractions, one job per function, max 30 lines, flat over nested with early returns, descriptive names, comments explain why.
critical-review
4-phase adversarial review protocol: pre-flight analysis, adversarial execution check, self-correction loop, and [VALIDATION] report.
agent-delegation
Rules for when and how to spawn sub-agents: Explore for 3+ file reads, parallel agents for independent tasks, summaries only — raw output never enters main context.
memory-first
Lookup chain enforced before any file read or search: project and global memory, grep/glob, targeted read — stop at the first step that answers.
verbosity
Response verbosity protocol: reads the level from /.claude/memory/verbosity.md and applies the MIN, INFO or VERBOSE output rules to every reply.
project-bootstrap
A workflow for adapting the smyslokod-starter project template to a specific product idea. It chooses a depth of setup and uses the template's business and project files as starting context.