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 skills add genudo-ai/genudo_mcp --skill remediate-agent-defectsgit clone --depth 1 https://github.com/genudo-ai/genudo_mcpWrote 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/genudo-ai/genudo_mcp/remediate-agent-defects)<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/remediate-agent-defects"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/remediate-agent-defects/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/skills/genudo-ai/genudo_mcp/remediate-agent-defects"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/remediate-agent-defects.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 | $0.00088 | $0.00752 |
| Opus 5.5 | $0.00035 | $0.00301 |
| Sonnet 5.5 | $0.00018 | $0.00150 |
| Haiku 4.5 | $0.00009 | $0.00075 |
Grade A, and why
remediate-agent-defects 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remediate Agent Defects
Fix the root cause with the narrowest edit, then re-test. Broad prompt rewrites trade one fixed journey for two broken ones.
1. Attribute each defect
Classify every failure before touching anything:
| Symptom | Root cause | Fix target | Tool |
|---|---|---|---|
| Wrong or missing fact (price, policy, spec) | Knowledge gap or conflict | Knowledge row | upsert_knowledge_points |
| Action fired too early or not at all | Stage instruction lacks an explicit trigger | Stage instructions | update_stage |
| Opportunity stuck in or jumped to the wrong stage | Vague or overlapping enter condition | Enter condition | update_stage |
| Tone, leak, invented discount, banned phrase | Missing hard rule | Pipeline global instructions | update_pipeline |
| Wrong payload field, bad phone, malformed webhook | Variable or action config | Action / variable | build-action-webhook, manage-pipeline-variables |
Group failures that share a cause — five failed steps are often one missing sentence.
2. Draft the surgical change
Rules of thumb:
- Facts live in knowledge tables, not instructions — prices and policies change, and a knowledge row updates without retesting the whole prompt.
- Workflow lives in stage instructions — when to ask, when to summarize, when to fire.
- Global instructions hold persona and hard limits only.
- Prefer explicit negatives with a replacement: "NEVER fire the order action before the customer confirms the summary; instead present items + shipping + total and ask for confirmation."
- Never encode one test customer's name, city, or phone into an instruction.
Typical patterns:
- Premature order → require an explicit confirmation turn before the order action fires.
- Invented discount → hard rule: never invent discounts or bundles; restate the active offers from the knowledge table instead.
- Missed stage move → rewrite the enter condition around the customer's observable intent ("has already ordered and asks about delay, courier, return, or change").
- Unverified assumption → add the missing fact as a knowledge row with the business's approved answer.
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 · 63 lines · 88 tokens per session scan A d10934ac7df8
remediate-agent-defects is a skill published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 88 tokens to every session and 752 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart. Do not use for ordinary review, style feedback, or general improvement suggestions.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.