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/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/claude)<a href="https://agentmods.dev/commands/marioepkone/pipelineiq/claude"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/claude/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/marioepkone/pipelineiq/claude"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/claude.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 | $0.00000 | $0.00547 |
| Opus 5.5 | $0.00000 | $0.00219 |
| Sonnet 5.5 | $0.00000 | $0.00109 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
CLAUDE 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 2mo 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 — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
commands/ — Context for Claude
(Scoped to this directory only. See root CLAUDE.md for project-wide context.)
Architecture
The top-level .md files in commands/ are Claude Code slash commands. They are not called by each other directly -- pipeline.md reads reference files from references/pipeline/ and fills [VARIABLES] to build subagent prompts at runtime. pipeline-team.md does the same with references/pipeline-team/. The standalone commands (spec.md, impl-plan.md, impl.md, audit-implementation.md, fix.md) serve double duty as both user-facing commands and subagent instruction sources -- named agents read their own command files at startup rather than receiving embedded content from the orchestrator. learnings-review.md and spec-splitter.md are standalone user-facing commands that are not used as subagent instruction sources.
Invariants
- Line count matters. Several specs and audits have enforced line-count targets on
pipeline.mdandpipeline-team.md. Edits that add content may trigger audit failures in downstream pipeline runs if they push files past their targets. Checklearnings.mdfor past instances of this. - Reference files use bracket variables, not template literals. Placeholders like
[WORKTREE_PATH],[SPEC_FILENAME],[MASTER_REPO_PATH],[COMMANDS_PATH]are filled by the orchestrator (pipeline.md) before passing to subagents. Using$VARIABLEor${VARIABLE}syntax will not be substituted -- it will be passed literally to the subagent. phase6-merge.mdchecks forpackage.jsonbefore invoking patch-notes. Ifpackage.jsondoesn't exist at the project root (as is the case for this project currently), the patch-notes step is silently skipped.
Gotchas
phase3-impl.mdoverrides impl.md's Phase 7 and Phase 8. The reference template tells the subagent to commit automatically (skip the user prompt) and skip the merge phase. An edit toimpl.mdPhase 7/8 behavior won't affect pipeline-driven runs -- only standalone/implinvocations.- Re-audit appends to the existing audit file rather than creating a new one. The re-auditor agent reads its process from
references/pipeline/re-audit-process.mdand writes output into[AUDIT_FILENAME]as an addendum.
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.
- 2mo ago First seen · 22 lines · 0 tokens per session scan A 2a2973dc81e7
CLAUDE is a command published in the GitHub repository MarioEpkOne/PipelineIQ (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 547 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
review-plan
Critically review the current plan/approach before implementing — assumptions, gaps, blast radius, deploy safety.
explain-dev
Write a WhatsApp-ready, non-technical message explaining a development to the client.
feature
Run the full feature pipeline — explore → plan → implement → review → test — for the change described in the argument.
triage
Triage a bug report (PDF / markdown / text) — extract the issues, prioritize, then run the fix pipeline per issue.
fix
Diagnose and fix a bug — reproduce → locate → root-cause → fix → test.
review
Review the current diff for bugs, security issues, and regressions.