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/smicolon/ai-kitWrote 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/smicolon/ai-kit/failure-list)<a href="https://agentmods.dev/commands/smicolon/ai-kit/failure-list"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/failure-list/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/smicolon/ai-kit/failure-list"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/failure-list.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 | $0.00012 | $0.00448 |
| Opus 5.5 | $0.00005 | $0.00179 |
| Sonnet 5.5 | $0.00002 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
failure-list 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 1mo 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
List Failures
Display failures from the project's failure log.
Steps
-
Check if failure log exists at
.claude/failure-log.local.md:- If not, inform user: "No failure log found. Use
/failure-addto start logging mistakes."
- If not, inform user: "No failure log found. Use
-
Read the failure log file
-
Parse optional category filter from arguments:
- If category provided, filter entries by that category
- Valid categories:
imports,security,testing,architecture,conventions - If no category, show all entries
-
Display failures in a readable format:
Output Format
📋 Failure Log Summary
━━━━━━━━━━━━━━━━━━━━━
Total entries: X
Last updated: YYYY-MM-DD
## Pattern Mistakes (X entries)
1. [2026-01-01] Brief title
Category: imports
Mistake: What went wrong
Correct: What to do instead
2. [2026-01-01] Another title
...
## Failed Approaches (X entries)
1. [2026-01-01] Brief title
Category: testing
What failed: Why it didn't work
Better: What works instead
━━━━━━━━━━━━━━━━━━━━━
Filtered Output
When category is provided:
📋 Failure Log: imports
━━━━━━━━━━━━━━━━━━━━━
Showing X entries for category: imports
1. [2026-01-01] Wrong import pattern
Mistake: Used relative imports
Correct: Use alias pattern
...
Empty Log
If log exists but has no entries:
📋 Failure Log
━━━━━━━━━━━━━━
No failures logged yet.
Use `/failure-add "description"` to log a mistake.
Usage Examples
/failure-list- Show all failures/failure-list imports- Show only import-related failures/failure-list security- Show only security-related failures
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.
- 1mo ago First seen · 90 lines · 12 tokens per session scan A 00f5a48d1543
failure-list is a command published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 448 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
diagnostic
Command "diagnostic" from datacore-one/datacore, covering diagnostic, command context, when to reference dip-0002, quick reference and agents this command invokes.
triage
Query open Node bugs, classify by priority and sub-team, suggest assignments, and generate a triage summary.
audit
Audit closed tickets for regressions against today's code (unchanged, evolved, implemented wrong, not implemented), plus duplicate and groupable open ones.
harness:maintenance-pipeline
On-demand, report-first maintenance sweep — runs overdue checks via harness maintenance run, triages findings, and asks the human in plain text before dispatching any fix.
fix-issues
Pick up one approved task, implement the fix, and close it.
project
Command "project" from getsentry/sentry-mcp, covering examples, list all projects in an org, filter by platform, view project details and open project in browser.