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/pipeline)<a href="https://agentmods.dev/commands/marioepkone/pipelineiq/pipeline"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/pipeline/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/pipeline"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/pipeline.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 | $0.04526 |
| Opus 5 | $0.00000 | $0.02263 |
| Sonnet 5 | $0.00000 | $0.00905 |
| Haiku 4.5 | $0.00000 | $0.00453 |
Grade A, and why
pipeline 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 9d 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLOSED-LOOP PIPELINE -- runs the complete spec -> impl-plan -> impl -> audit -> fix loop -> summary workflow. The spec phase is interactive (inline). Each subsequent phase runs as an isolated subagent with clean context. If errors are found during audit, a fix->re-audit loop runs automatically (max 2 cycles).
The user's request/feature description is: $ARGUMENTS
Argument Parsing
Parse $ARGUMENTS for the SKIP_MERGE=true sentinel:
- Match
SKIP_MERGE=trueonly as a whitespace-delimited token (not as a substring of a filename or path). In practice this means: split arguments on whitespace, check if any token is exactlySKIP_MERGE=true, remove that token, rejoin the rest. - If found: set SKIP_MERGE = true; the remaining text is the user's request / spec path.
- If not found: SKIP_MERGE = false (default).
SKIP_MERGE is used in Phase 6 to control whether the merge workflow runs. When /pipeline is invoked standalone by a user, SKIP_MERGE is never present.
SKIP_MERGE contract (do not change without updating pipeline-team.md):
- When SKIP_MERGE=true, Phase 6 MUST output:
PIPELINE_COMPLETE spec=<path> worktree=<path> branch=<name> working_log=<path> audit=<path> remaining_errors=<N> - pipeline-team.md depends on this exact output format for teammate coordination.
Resolve COMMANDS_PATH
Determine the absolute path to this plugin's commands/ directory.
Discovery order:
- Read
~/.claude/plugins/installed_plugins.json. Parse as JSON. Find any key matchingpipelineiq@*(match plugin name prefix, ignore marketplace suffix). If multiple matches: collect all entries across all matching keys, sort bylastUpdateddescending, take the first. Set COMMANDS_PATH = /commands. - If the registry file does not exist, is unreadable, or contains no
pipelineiq@*key: walk up from CWD looking for.claude-plugin/plugin.jsonwhere the adjacentcommands/directory containspipeline.md. If found: COMMANDS_PATH = <that commands/ directory> - If neither found: STOP with "Cannot locate PipelineIQ plugin. Ensure the plugin is installed via the plugin marketplace, or you are in the PipelineIQ repo."
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.
- 9d ago First seen · 374 lines · 0 tokens per session scan A 8b5c3f56894c
pipeline is a command published in the GitHub repository MarioEpkOne/PipelineIQ (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,526 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
code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding.
handoff-verify
A pre-merge review command that sends a code change to several reviewers, then rechecks serious findings. Pre-merge means before the change is added to the main codebase.
clean-pr-comments
Review PR comments - fix bad naming, preserve necessary context.
architecture-review
Architecture + code-health audit — module boundaries, then fallow on TS/JS — and a task per finding.
flow-lint
Examine workflow JSON files against clean coding practices, naming standards, and error-handling fallbacks.
review
Run a full code review using the code-review-coordinator agent.