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 commands/alleneubank/claude-code/specoutgit clone --depth 1 https://github.com/alleneubank/claude-codeWhat 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 | $0.00008 | $0.00577 |
| Opus 5 | $0.00004 | $0.00289 |
| Sonnet 5 | $0.00002 | $0.00115 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
specout 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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load the spec-best-practices skill before proceeding.
Spec File Selection
A spec file path is required. Check the argument provided: $ARGUMENTS
If no argument was provided (empty or blank):
- Search for existing
SPEC.mdfiles in the project (root, apps/, packages/, src/lib/*/) - Present any found files to the user and ask which to use
- If none found, determine the correct colocated path for a new
SPEC.mdand propose it - Do not proceed until a spec file is confirmed
If argument provided:
- If the filename is not
SPEC.mdand is not a supporting file linked from an existingSPEC.mdTOC, suggest the correctSPEC.mdpath instead - If the file doesn't exist, ask if you should create it at that path
Once the spec file is confirmed, read it using the Read tool.
Gap Analysis
Before interviewing, check the spec for required elements from spec-best-practices:
- Problem/Solution narrative
- Domain model (types, relationships)
- Requirements with
REQ-{DOMAIN}-{NNN}IDs - Invariants
- Non-goals
- Acceptance criteria (checklistable)
- Risk tags (if high-risk items exist)
Note which elements are missing or incomplete. Focus the interview on filling these gaps.
Interview Process
Interview me using AskUserQuestionTool to fill gaps and clarify ambiguities. Ask about:
- Types, schemas, and data models (what are the core domain types? what invariants do they encode?)
- Technical implementation details and constraints
- UI/UX decisions and user flows
- Edge cases and error handling
- Tradeoffs and alternatives considered
- Integration points and dependencies
- Security, performance, and scalability concerns
- Non-goals and explicit scope boundaries
- Risk classification for high-risk items (schema migrations, auth, public APIs, infra)
<question_quality> Avoid surface-level questions I've likely already considered. Dig into:
- Second-order effects and unintended consequences
- Assumptions that haven't been validated
- Contradictions or tensions in the spec
- Missing success/failure criteria
- Operational concerns (monitoring, debugging, rollback)
- Invariants that should be explicitly stated
- Scope boundaries that need to be drawn as non-goals </question_quality>
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.
- 2d ago First seen · 64 lines · 8 tokens per session scan A d9a56f1907aa
specout is a command published in the GitHub repository alleneubank/claude-code (52 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 8 tokens to every session and 577 once invoked, about $0.0000 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 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.