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/JairoTorregrosa/jaiskillsWrote 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/jairotorregrosa/jaiskills/triage)<a href="https://agentmods.dev/commands/jairotorregrosa/jaiskills/triage"><img src="https://agentmods.dev/badge/commands/jairotorregrosa/jaiskills/triage/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/jairotorregrosa/jaiskills/triage"><img src="https://agentmods.dev/badge/commands/jairotorregrosa/jaiskills/triage.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 | $0.00025 | $0.00786 |
| Opus 5 | $0.00013 | $0.00393 |
| Sonnet 5 | $0.00005 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
triage 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 10d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Pending TODOs
DO NOT CODE ANYTHING DURING TRIAGE. This command is for decision-making only. Implementation happens in /jaiskills:resolve-todos.
Steps
1. Load Pending TODOs
Read all todos/*-pending-*.md files using Glob.
If an argument was provided (e.g., a specific ID like 003 or a pattern like p1), filter to only matching files.
If no pending TODOs found, tell the user: "No pending TODOs to triage. Create some from review findings first."
2. Sort by Priority
Order the pending TODOs for presentation:
- p1 (Critical) first
- p2 (Important) second
- p3 (Nice-to-have) last
Within the same priority, sort by ID (ascending).
3. Present Each TODO
For each pending TODO, display a summary card:
--- Finding [N] of [M] ---
[P1 CRITICAL | P2 IMPORTANT | P3 NICE-TO-HAVE]
Title: [title from the TODO heading]
Tags: [tags from frontmatter]
Location: [file:line references from Findings section]
Problem: [first 2-3 sentences of Problem Statement]
Proposed Solution: [summary of recommended option or first option]
Effort: [effort estimate from proposed solution]
Dependencies: [dependency IDs if any]
4. User Decision
Use AskUserQuestion for each TODO with these options:
- Approve: Accept this finding for implementation
- Skip: Remove this TODO — not worth fixing or not actionable
- Modify: Let the user provide changes (priority, description, solution) before approving
On Approve:
- Rename the file from
pendingtoready:mv todos/{id}-pending-{priority}-{desc}.md todos/{id}-ready-{priority}-{desc}.md - Update the
statusfield in YAML frontmatter frompendingtoready - Update the
updateddate in YAML frontmatter
On Skip:
- Delete the TODO file:
rm todos/{id}-pending-{priority}-{desc}.md
On Modify:
- Ask the user what to change (priority, recommended action, description, etc.)
- Apply the modifications to the file content
- Then rename from
pendingtoready(same as Approve) - Update
statusandupdatedfields in frontmatter
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.
- 10d ago First seen · 104 lines · 25 tokens per session scan A bb6732030297
triage is a command published in the GitHub repository JairoTorregrosa/jaiskills (5 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 786 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
bug-check
Run automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
pn-audit-data
Design or review database schema — normalization, indexing strategy, migration plan, and data model decisions. Surgical command for database design. Use standalone or as part of pn-backend-audit.
review-router
Route to the appropriate quality or review command based on the user's intent.
pn-audit-api
Surgical API design review — REST conventions, status codes, response shapes, validation, and schema leaks. Use standalone or as part of pn-backend-audit. Outputs a scored fix roadmap.
pn-audit-security
OWASP-guided security review — auth posture, input validation, secrets, CORS, JWT, rate limiting. Surgical command for backend security. Use standalone or as part of pn-backend-audit.