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/marioepkone/pipelineiq/specgit clone --depth 1 https://github.com/MarioEpkOne/PipelineIQWrote 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/marioepkone/pipelineiq/spec)<a href="https://agentmods.dev/commands/marioepkone/pipelineiq/spec"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/spec.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 5.1 | $0.00000 | $0.00670 |
| Opus 5 | $0.00000 | $0.00335 |
| Sonnet 5 | $0.00000 | $0.00134 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
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 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You investigate what the user wants to build, orient yourself in the codebase, then interview the user in depth to produce a complete specification.
The user's request is: $ARGUMENTS
Constraints
Read-only. Do not modify any codebase files. Your only written output is the spec document.
Do not take actions that affect external systems (no git, no PRs, no API calls).
Process
Phase 1: Orient
Read the user's request carefully. Identify what parts of the codebase are relevant.
Explore the codebase. Understand the current state of the relevant code: architecture, data flow, conventions, constraints, existing patterns. Use whatever tools and approaches get you there.
Verify your understanding. Don't assume. Read the actual code. If something is ambiguous, verify it independently.
Summarize what you found back to the user in a few sentences. Confirm you're looking at the right area and that your mental model matches reality.
Spend real effort here. The quality of your interview depends entirely on how well you understand the current code. You can't ask non-obvious questions about code you haven't read.
Phase 2: Interview
Interview the user in detail using the AskUserQuestion tool about literally anything -- technical implementation, UI and UX, concerns, trade-offs, and so on. Make sure the questions are not obvious. Be very in-depth and continue interviewing continually until the interview is complete. Then write the spec to the file.
Phase 3: Write the Spec
When the interview is complete, write the spec document to the specs/ directory in the project root. Before writing the file, run date '+%Y-%m-%d--%H-%M' in the project root to get the actual current timestamp. Use that output as the YYYY-MM-DD--HH-MM portion of the filename: spec--YYYY-MM-DD--HH-MM--<short-description>.md.
The spec must contain these sections:
Goal: What we're building and why.
Current State: What exists today (from Phase 1).
Decisions: Every decision made during the interview, with rationale.
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 · 56 lines · 0 tokens per session scan A 0d41f447ab3c
spec is a command published in the GitHub repository MarioEpkOne/PipelineIQ (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 670 tokens. 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
publish
Publish repository to GitHub with full setup.
release
Create a GitHub release with auto-generated changelog.
probe
Probe recent changes with 2-3 pointed questions.
prime
Load project context and output a structured summary.
lint
Run markdownlint on specified files or the whole project.
skill-stats
Leaderboard of your most-used skills from the durable usage log (survives transcript cleanup).