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/learnings-review)<a href="https://agentmods.dev/commands/marioepkone/pipelineiq/learnings-review"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/learnings-review/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/learnings-review"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/learnings-review.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 | $0.03326 |
| Opus 5 | $0.00000 | $0.01663 |
| Sonnet 5 | $0.00000 | $0.00665 |
| Haiku 4.5 | $0.00000 | $0.00333 |
Grade A, and why
learnings-review 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 11d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review learnings.md, classify each entry as universal or project-specific, route approved entries to commands/*.md or project KB files, curate existing KB entries, and archive everything to promotion-log.md.
The user's request is: $ARGUMENTS
Step 1 -- Read learnings.md
Read learnings.md at the project root. If running from a project other than PipelineIQ, locate PipelineIQ's root by finding where commands/pipeline.md is installed and resolving upward. If empty or contains only headers with no entries, tell the user and stop.
Parse all entries. Group by severity tier (HIGH, MEDIUM, LOW). Number them 1, 2, 3... for reference throughout this workflow, ordered by severity (HIGH first, then MEDIUM, then LOW) and within each tier by occurrence count (highest first).
Step 1.5 -- Detect target project context
Determine whether project-specific routing is available:
- Check if the current working directory (target project root) has a
.claude/directory - Check if the target project root has a
CLAUDE.mdfile - If neither
.claude/norCLAUDE.mdexists: set PROJECT_KB_AVAILABLE = false, warn the user ("Project-specific routing unavailable -- no .claude/ directory or CLAUDE.md found. All learnings will be treated as universal pipeline improvements."), proceed with universal-only workflow - If
.claude/exists butCLAUDE.mddoes not: project-specific routing is partially available -- agent-specific KB files CAN be created in.claude/pipeline-kb/but project-wide gotchas cannot be routed toCLAUDE.md. Warn user about the limitation. - If both exist: set PROJECT_KB_AVAILABLE = true, read any existing
.claude/pipeline-kb/*.mdfiles for the curation step
Step 2 -- Analyze each entry against the codebase
For each entry, in order of severity (HIGH first):
- Read the target file referenced in Suggested diff
- Verify the diff still applies (the old text exists in the file at roughly the expected location)
- Check whether the problem described actually exists in the current command file
- Assess whether the suggested change would conflict with or contradict existing logic
- Check the real benefit: Is this a meaningful improvement, or cosmetic/trivial?
- If the diff is stale (old text not found in target file), attempt to regenerate it by re-reading the target file and the suggestion. If unable to generate a valid diff, mark as "stale -- needs manual review"
- If the problem described in the learning has already been fixed in the current file, mark as "Already resolved" with evidence (cite the line/section where the fix exists)
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.
- 11d ago First seen · 225 lines · 0 tokens per session scan A d1f99a2fe9f9
learnings-review 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 3,326 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
learn
A command for recording lessons learned from direct notes, recent errors, or the current work session. It can classify lessons, suggest automations from git history, and manage the saved list.
stash
Stash session context [name].
teach
Hand-record a lesson into Memory Fabric (learning tier, high confidence) so it is recalled later.
remember
Consolidate stashes + friction into project memory.
sessions
Manage Claude Code session history, aliases, and session metadata.
save-session
Save current session state to a dated file in /.claude/session-data/ so work can be resumed in a future session with full context.