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/fix)<a href="https://agentmods.dev/commands/marioepkone/pipelineiq/fix"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/fix/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/fix"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/fix.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 | $0.01191 |
| Opus 5.5 | $0.00000 | $0.00476 |
| Sonnet 5.5 | $0.00000 | $0.00238 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
fix 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TARGETED FIX — reads an audit document's "Actionable Errors" section and fixes each error. Can be used standalone or invoked by the pipeline.
The user's request is: $ARGUMENTS
Phase 1 — Find Inputs
Search Working Logs/ for an audit document whose filename starts with audit-impl-- and contains the argument (case-insensitive).
- If multiple matches: list them and ask the user to pick one.
- If no match and argument looks like a file path: try reading it directly.
- If no match: tell the user no audit found and exit.
- If no argument: use the most recently modified file in
Working Logs/whose name starts withaudit-impl--.
Read the audit document in full.
Parse the "Actionable Errors" section. If no such section exists: tell the user "This audit does not have a structured Actionable Errors section. Run /audit-implementation with the latest skill version to generate one." and exit.
From the audit header, read:
- The referenced impl plan from
Implementation Plans/ - The referenced working log from
Working Logs/(if it exists)
Phase 2 — Read Context
For each actionable error entry, read every file listed in its File(s) field.
If the audit references a worktree in its header, resolve and use that worktree as the working root for file reads and edits.
Phase 3 — Fix Each Error
For each actionable error (skip entries under "Not actionable"):
- Read the relevant file(s) fresh (they may have changed since the audit)
- Apply the suggested fix using Edit/Write
- After each fix: verify no errors were introduced by running the project's build/lint/test command as appropriate
- If a fix introduces new errors:
- Revert the change
- Try a different approach (max 2 attempts per error)
- If both attempts fail: mark as "fix failed" with explanation
- If the suggested fix doesn't apply (file changed, method renamed, etc.): mark as "deferred to user" with explanation
Log each fix result as you go — do not batch.
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 · 121 lines · 0 tokens per session scan A 294c0d023755
fix 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 1,191 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
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.
dbg
Alias — systematic debugging via superpowers:systematic-debugging.
jira-duplicate-bugs
Find potential duplicate bugs in a Jira project. Provide PROJECTKEY here: $ARGUMENTS.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.