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.
git clone --depth 1 https://github.com/JobsHwang/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/commands/jobshwang/skills/to-spec)<a href="https://agentmods.dev/commands/jobshwang/skills/to-spec"><img src="https://agentmods.dev/badge/commands/jobshwang/skills/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/commands/jobshwang/skills/to-spec"><img src="https://agentmods.dev/badge/commands/jobshwang/skills/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 | $0.00025 | $0.00393 |
| Opus 5 | $0.00013 | $0.00197 |
| Sonnet 5 | $0.00005 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00039 |
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 8d 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.
What it actually says
The user explicitly invoked /to-spec.
Invocation arguments: $ARGUMENTS
To Spec
Produce a technical delivery contract, not an implementation transcript.
- Use the current conversation or supplied PRD as the product source. Do not repeat requirement discovery unless one unresolved decision would invalidate the design.
- Inspect the repository, its
AGENTS.mdor equivalent instructions, existing implementation seams, build configuration, and relevant tests before designing. - Resolve durable coding-spec roots in this order:
- an explicit project convention or configured path;
.agents/spec;.trellis/spec;docs/spec.
- Read only the relevant durable specs. If an existing project uses
.trellis/spec, keep it canonical; do not create.agents/specbeside it. For a new project with no established root,.agents/specis the neutral default. - Use references/spec-template.md selectively and consult references/delivery-surfaces.md only for surfaces present in the change.
- Ground decisions in repository evidence. State assumptions and open questions instead of inventing facts.
- Specify observable behavior, boundaries, contracts, data flow, errors, compatibility, migration, and proportionate verification. Avoid line-by-line implementation instructions.
Write beside the source PRD when possible. Otherwise use .scratch/<feature>/spec.md. Working PRDs and delivery specs stay under .scratch; durable coding conventions stay in the resolved spec root. Never migrate or duplicate a Trellis spec tree silently.
Do not implement. Report the path and the main design decisions. Suggest slice-spec only when the work is too large for one coherent delivery session, crosses several independently risky seams, or needs staged rollout.
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.
- 8d ago First seen · 28 lines · 25 tokens per session scan A bcfc806de3ca
to-spec is a command published in the GitHub repository JobsHwang/skills (2 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 393 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.