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/advisorgit 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/advisor)<a href="https://agentmods.dev/commands/koolamusic/claudefiles/advisor"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/advisor.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 | $0.00041 | $0.00940 |
| Opus 5 | $0.00020 | $0.00470 |
| Sonnet 5 | $0.00008 | $0.00188 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
advisor 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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get a second opinion before committing to a triage decision or plan. The advisor is an independent agent that reads the same artifacts but approaches them from a skeptical stance.
Parse the input
$ARGUMENTS:
triage— advise on a triage recommendation (issue labels, state transition, agent brief)plan— advise on sprint plans (wave structure, task decomposition, risk coverage)--sprint <slug>— target a specific sprint (default: active)
If empty, infer from sprint state:
- If plans exist but no EXECUTION.md: assume
plan - If no plans: assume
triage - If ambiguous: ask
Context gathering
For triage advisory
Read:
- The issue under triage (from
gh issue viewor the sprint's BRIEF.md) - Any existing triage notes or comments
.jira/STATE.md— prior sprint patterns and decisions log.project/PROJECT.md— project-level goals (does this issue align?).project/ROADMAP.md— is this the right time for this work?
For plan advisory
Read:
- All
*-PLAN.mdfiles in the sprint CONTEXT.md— locked decisionsRESEARCH.md— original research findingsBRIEF.md— the original problem statement
Spawn the advisor agent
Single Agent call with the jira-advisor agent:
You are the advisor — an independent reviewer challenging the current <triage|plan> recommendation.
## Your inputs
<all gathered context>
## Your job
Produce a structured advisory with three sections:
1. **Challenges** — assumptions in the <recommendation|plan> that might be wrong. For each:
- What's assumed
- Why it might not hold
- What breaks if it doesn't
- Severity: BLOCKER / RISK / MINOR
2. **Alternatives** — different approaches the <triage|planner> didn't consider. For each:
- What it is
- What it costs vs the current approach
- When you'd pick it over the current approach
3. **Endorsements** — parts of the <recommendation|plan> that are solid. Don't manufacture criticism for things that hold up.
## Rules
- Be specific. "This might not scale" is noise. "The N+1 query on line 45 of 02-PLAN.md will timeout with >1000 entries because..." is signal.
- Reference artifacts by path and section.
- Don't rewrite the plan. Challenge it.
- If everything looks solid, say so in 3 lines. Don't pad.
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.
- 3d ago First seen · 100 lines · 41 tokens per session scan A 52fa214bb1de
advisor is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 940 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
git
Git operations with intelligent commit messages and workflow optimization.
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.