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/tercel/spec-forgeWrote 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/tercel/spec-forge/srs)<a href="https://agentmods.dev/commands/tercel/spec-forge/srs"><img src="https://agentmods.dev/badge/commands/tercel/spec-forge/srs/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/tercel/spec-forge/srs"><img src="https://agentmods.dev/badge/commands/tercel/spec-forge/srs.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 | $0.00041 | $0.02150 |
| Opus 5.5 | $0.00016 | $0.00860 |
| Sonnet 5.5 | $0.00008 | $0.00430 |
| Haiku 4.5 | $0.00004 | $0.00215 |
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 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 — 120 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: $ARGUMENTS
This document is the delivery contract. It is what an implementation team — an external vendor, another team, or code-forge — is held to, and what acceptance is settled against. The upstream PRD answers "is this worth building"; this document answers "exactly what must be built, and how do we determine whether it was". That distinction drives six sections a merely descriptive requirements document omits, and which this command treats as mandatory wherever they apply: scope boundaries with an explicit out-of-scope table, input field rules per requirement, state machines including illegal-transition handling, a permission matrix with denial behavior, an error catalogue with degradation behavior per dependency, and acceptance and change control.
Workflow
Step 1: Project Context Scanning
Before anything else, scan the current project to understand context:
- Use Glob to scan the project directory tree (top 3 levels)
- Read the project README.md if it exists
- Scan the
docs/directory for existing documents - Detect (do NOT read) matching PRD document: check if
docs/*/prd.mdrelated to "$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).
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 Changed · +15 lines · +18 tokens per session d898c6a44894
- 1mo ago First seen · 105 lines · 23 tokens per session scan A 45db550a6767
srs is a command published in the GitHub repository tercel/spec-forge (10 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 2,150 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
cs-grill-agent-launcher
Matt Pocock docs-anchored grill for an agent-launcher goal — walks the phase's forcing questions ONE at a time, each with a recommended answer and a citation to a reference doc, refusing to advance on a fuzzy input. Use to pressure-test a CMA plan before launching.
promote
The promote loop — scan your transcripts for what you keep asking, pick a pattern, draft the skill, test its triggers, publish the release package.
rescue-an-account
Workflow recipe — diagnose an at-risk customer and build the full save play through to renewal by chaining 4 skills.
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
prompt-optimizer
Analyze and rewrite a prompt to maximize clarity, specificity, and output quality.
checklist
Generate a custom checklist for the current feature based on user requirements.