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 skills/ninemindai/agentgem/agentgem-retronpx skills add ninemindai/agentgem --skill agentgem-retrogit clone --depth 1 https://github.com/ninemindai/agentgemWrote 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/skills/ninemindai/agentgem/agentgem-retro)<a href="https://agentmods.dev/skills/ninemindai/agentgem/agentgem-retro"><img src="https://agentmods.dev/badge/skills/ninemindai/agentgem/agentgem-retro.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 | $0.00059 | $0.00441 |
| Opus 5 | $0.00030 | $0.00220 |
| Sonnet 5 | $0.00012 | $0.00088 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
agentgem-retro 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 6d 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.
What it actually says
agentgem-retro
A focused friction retro — the "Where Things Go Wrong" slice of an insights report, without the full pipeline. Findings come from AgentGem's deterministic session detectors; your job is to verify each one against a real transcript and turn it into one concrete, standing fix.
Procedure
- Collect. Call
get_behavior_findings(agentgem-goldmine MCP; default 14 days). Patterns are detector-derived: retry storms, thrash loops, unverified finishes, plus the user's own rules from~/.agentgem/detectors. - Verify before advising. For each finding, call
ask_sessionon the cited session and ask whether the flagged behavior actually occurred. Keep the finding only if the answer supports it; drop it and say so if not. Detectors are heuristics — a retry storm can be a flaky test, not a habit. - Advise. For each verified finding give: what happened (with the session it
happened in), why it costs time, and one fix the user can adopt permanently —
a custom detector rule in
~/.agentgem/detectors, a workflow change, or a skill worth installing (get_artifact_detailto inspect what's already installed). - Close the loop. Point at the standing surfaces:
agentgem learnto distill the lesson into the review queue, and the console Observe/Insights panels for the ongoing view.
Honesty rules
- Never advise from an unverified detector hit; every recommendation cites a session you actually read.
- If the findings are empty or all fail verification, say the recent sessions look clean — do not invent friction to have something to say.
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.
- 6d ago First seen · 36 lines · 59 tokens per session scan A 4102dba796dc
agentgem-retro is a skill published in the GitHub repository ninemindai/agentgem (39 stars, last pushed 9d ago), licensed MIT. It adds 59 tokens to every session and 441 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
memory-leak-debug
Diagnose memory leaks in the Qwen Code CLI using heap snapshots and the chrome-devtools CLI. Use when investigating high memory usage, unbounded growth, or suspected object retention issues.
bugfix
Fix a bug from a GitHub issue, following the reproduce-first workflow. Use when the user asks to fix a bug, investigate a GitHub issue, or debug a user-reported problem. Takes a GitHub issue URL or number as input.
rust-check
Run cargo check on the current Rust project to find compile errors.