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 commands/koolamusic/claudefiles/triagegit clone --depth 1 https://github.com/koolamusic/claudefilesWrote 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/koolamusic/claudefiles/triage)<a href="https://agentmods.dev/commands/koolamusic/claudefiles/triage"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/triage.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 | $0.00037 | $0.01186 |
| Opus 5 | $0.00018 | $0.00593 |
| Sonnet 5 | $0.00007 | $0.00237 |
| Haiku 4.5 | $0.00004 | $0.00119 |
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 5d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decompose sprint plans into GitHub issues — one issue per vertical slice that cuts through all layers end-to-end.
Parse the input
$ARGUMENTS:
--plan N— decompose only plan N (default: all plans)--dry-run— show the breakdown without creating issues
Locate the sprint
slug=$(cat .jira/CURRENT)
sprint_dir=".jira/sprints/${slug}"
Stop if no active sprint or no plans exist.
Steps
1. Gather context
Read:
- All
*-PLAN.mdfiles (or targeted plan) CONTEXT.md— locked decisions constrain slice boundariesBRIEF.md— the original problem statement (issues reference back to it).project/PROJECT.mdif it exists — project vocabulary for issue titlesCLAUDE.md— domain glossary
2. Explore the codebase
Before slicing, understand the layers the slices will cut through. Identify:
- Data layer (schema, migrations, models)
- API/service layer (routes, handlers, services)
- UI layer (components, pages, routes) — if applicable
- Test layer (existing test patterns, fixtures)
3. Draft vertical slices
Break each plan into tracer bullet slices. Each slice is a thin vertical cut through ALL layers, not a horizontal slice of one layer.
For each slice, determine:
- Title — short, uses project vocabulary
- Type — AFK (agent can implement) or HITL (needs human judgment)
- Blocked by — other slice IDs that must complete first
- Acceptance criteria — specific, testable, covers the full vertical
- Wave — which wave from the source plan this slice belongs to
Slice rules:
- Each slice delivers a narrow but COMPLETE path through every layer
- A completed slice is demoable or verifiable on its own
- Prefer many thin slices over few thick ones
- AFK slices should be detailed enough that a sub-agent can implement without asking questions
4. Present the breakdown
## Issue Breakdown — <slug>
Source: <plan count> plans across <wave count> waves
Slices: <total> (<AFK count> AFK, <HITL count> HITL)
| # | Title | Type | Wave | Blocked by | Criteria |
|---|---|---|---|---|---|
| 1 | ... | AFK | 1 | — | 3 |
| 2 | ... | AFK | 1 | — | 2 |
| 3 | ... | HITL | 2 | 1 | 4 |
Proceed?
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.
- 5d ago First seen · 153 lines · 37 tokens per session scan A d8eba6b375ff
triage is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 6d ago), licensed MIT. It adds 37 tokens to every session and 1,186 once invoked, about $0.0002 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.