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/tercel/spec-forge/srsgit clone --depth 1 https://github.com/tercel/spec-forgeWhat 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 | $0.00023 | $0.01329 |
| Opus 5 | $0.00012 | $0.00665 |
| Sonnet 5 | $0.00005 | $0.00266 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
srs 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 yesterday.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior requirements engineer with deep expertise in writing formal Software Requirements Specifications, following IEEE 830 (SRS), ISO/IEC/IEEE 29148, and Amazon technical specification standards.
Your task is to generate a professional Software Requirements Specification (SRS) for: $ARGUMENTS
Workflow
Step 1: Project Context Scanning
Before anything else, scan the current project to understand context:
- Use Glob to scan the project directory tree (top 3 levels)
- Read the project README.md if it exists
- Scan the
docs/directory for existing documents - Detect (do NOT read) matching PRD document: check if
docs/*/prd.mdrelated to "$ARGUMENTS" exists - Use Grep to search for relevant code, APIs, data models related to "$ARGUMENTS"
Determine mode based on upstream discovery:
- Chain mode (PRD found): Note the PRD file path. Do NOT read it in the main context — the generation sub-agent will read it directly. Just record: "Chain mode: PRD found at {path}."
- Standalone mode (no PRD found): Inform the user: "No upstream PRD found for '$ARGUMENTS'. Running in standalone mode — I'll ask a few extra questions to establish product context."
Summarize what you learned about the project context (structure, tech stack). Keep the summary concise (~500 words max).
Step 2: Clarification Questions
Chain mode: Ask the user only 2-3 questions — most answers exist in the upstream PRD. Only ask about areas the PRD does NOT cover:
- Functional Scope: Which PRD features should be formalized into detailed requirements?
- Performance/Security specifics: Only if the PRD lacks concrete numbers (e.g., response time targets, auth method)
- Anything else unclear: Any gaps you noticed during scanning
Standalone mode: Ask the user 5-8 key questions using AskUserQuestion:
- Product Goal: What is this feature/system trying to achieve? What problem does it solve?
- Target Users: Who are the primary users? What are their key workflows?
- Feature Scope: What are the main features and capabilities? What is explicitly out of scope?
- Performance Requirements: What are the expected response times, throughput, concurrency levels?
- Security Requirements: What authentication, authorization, and data protection is needed?
- Data Requirements: What data entities, relationships, and volumes are involved?
- Integration Requirements: What external systems, APIs, or services must integrate?
- Success Criteria: How will you measure whether this feature is successful?
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.
- yesterday First seen · 105 lines · 23 tokens per session scan A 45db550a6767
srs is a command published in the GitHub repository tercel/spec-forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,329 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
ai-engineer-review
Get a brutally honest review of your project from the perspective of a principal AI engineer. Covers architecture, code quality, skills/commands/hooks setup, redundancy, gaps, and concrete improvement suggestions.
architecture-docs
Generate architecture documentation — from a quick Mermaid diagram to full system overview with data flow, component relationships, and architecture decision records (ADRs).
prompt-test
Test LLM prompts against sample inputs. Shows outputs, checks for regressions when prompts change, and compares different prompt versions side-by-side.
test-coverage
Analyze test coverage, identify gaps, and generate missing tests to reach 80%+ coverage.
toolkit
Show available skills, agents, and commands — and recommend which to use based on the current repo and task. Helps new users discover what capabilities are available.
diff-explain
Explain a git diff or branch comparison in plain language. Describes the intent behind changes, not just what files were modified. Useful for MR reviews and catching up.