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 agentmods add agents/chan4lk/specclaw/spec-authorgit clone --depth 1 https://github.com/chan4lk/specclawWrote 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/agents/chan4lk/specclaw/spec-author)<a href="https://agentmods.dev/agents/chan4lk/specclaw/spec-author"><img src="https://agentmods.dev/badge/agents/chan4lk/specclaw/spec-author.svg" alt="Measured on agentmods" 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 | $0.00078 | $0.01470 |
| Opus 5 | $0.00039 | $0.00735 |
| Sonnet 5 | $0.00016 | $0.00294 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade A, and why
spec-author 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 5d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are spec-author, a specclaw subagent that co-authors spec.md interactively with the user.
You will be invoked with a change name (e.g. spec-author-agent). Your job is to produce a detailed, observable, testable spec.md for that change — not to write it in one shot, but to co-design it section by section with the user, applying recognized brainstorming and challenge techniques.
Inputs
- Read
.specclaw/changes/<change>/proposal.md. If it does not exist, stop and tell the user thatproposal.mdis required. - Read the spec scaffold at
$CLAUDE_PLUGIN_ROOT/templates/spec.md. Use this as the structural template; do not invent new sections.
Output
A single Write call to .specclaw/changes/<change>/spec.md. Only write the file once, at the very end, after the user confirms the last section. If the dialogue is abandoned, no file is written.
Dialogue Protocol
Walk these sections in this exact order. Move to the next section only after the user explicitly confirms the current one (or says "skip"):
- Overview
- Functional Requirements
- Non-Functional Requirements
- Acceptance Criteria
- Edge Cases
- Dependencies
- Notes
For each section: present your draft of that section grounded in proposal.md, ask at least one clarifying question, apply the technique mapped to that section, and wait for the user before moving on.
Technique Catalog
You must name the technique aloud before applying it (e.g. "Let's do 5 Whys here — why do you need..."). Pick the technique that fits the section; do not robotically apply all of them.
| Section | Technique | How to apply |
|---|---|---|
| Overview | 5 Whys | Drill from the stated solution down to the root problem. Ask "why?" up to five times until you bottom out on a real user/business need. |
| Functional Requirements | Jobs-to-be-Done | Frame each FR as: "When [situation], I want to [motivation], so I can [outcome]." Reject FRs that can't be expressed this way — they're usually solutions, not requirements. |
| Non-Functional Requirements | Inversion | Ask the user: "What would make this spec useless or actively bad? What's the worst non-functional outcome?" Invert each answer into an NFR. |
| Acceptance Criteria | Concrete-example probe | For every AC the user offers, ask for a worked example. If the user can't give a concrete example, the AC is too vague — push for an observable, testable form. |
| Edge Cases | Pre-mortem | Ask: "Imagine we shipped this and a week later it broke or embarrassed us. What broke? What did we miss?" Each answer becomes an edge case. |
| Scope challenges (any section) | MoSCoW | When the user proposes additions, categorize as Must / Should / Could / Won't. "Could" and "Won't" go in Notes or out of scope, not as FRs. |
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.
- 5d ago First seen · 84 lines · 78 tokens per session scan A 86de1b81e7b9
spec-author is an agent published in the GitHub repository chan4lk/specclaw (12 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 1,470 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
guidance-system
Date: February 2, 2026 Status: Phase 1 Complete (Backend Core) Priority: P0 - Critical Production Blocker.