Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add kenmulford/milestone-driver/plugin install milestone-driverWrote 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/kenmulford/milestone-driver/triage)<a href="https://agentmods.dev/skills/kenmulford/milestone-driver/triage"><img src="https://agentmods.dev/badge/skills/kenmulford/milestone-driver/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/skills/kenmulford/milestone-driver/triage"><img src="https://agentmods.dev/badge/skills/kenmulford/milestone-driver/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 | $0.00085 | $0.08687 |
| Opus 5 | $0.00043 | $0.04344 |
| Sonnet 5 | $0.00017 | $0.01737 |
| Haiku 4.5 | $0.00009 | $0.00869 |
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 today.
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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
triage - pre-build review phase
Review issues for design gaps and dependency ordering. Emit an all-clear or a gap table. Post a blocker summary on each affected issue. Return the validated dependency graph.
Contents
1 Profile · 2 Gather · 2.5 Cache lookup · Resolve docs · Resolve citations · 3 Dispatch · 3.5 Resolve · 4 Aggregate · 5 Output · 6 Comment · 6.5 Cache write · 7 Return
Announce first
Say this to the user before doing any work:
Standing by while I review the issue(s) for gaps and dependencies needing your input before building.
Modes
| Argument | Mode | Scope |
|---|---|---|
| Milestone name (string) | Batch | All open issues in that milestone |
| Issue number (integer) | Single | That one issue |
Procedure
Step 1 - Read the profile
Read the profile (docs/profile-schema.md). Resolution (transitional READ only - triage performs no migration move): <repo>/.milestone-config/driver.json first, else the legacy root <repo>/milestone-driver.json. Both present → .milestone-config/driver.json wins; no move, no overwrite, no deletion. On the legacy layout, triage surfaces a one-line note - "legacy profile detected - will migrate on the next build/setup". If neither file exists or a required Core key is missing, invoke milestone-driver:setup, then continue.
Extract:
| Key | Default |
|---|---|
triageAgent |
milestone-driver:triage-reviewer |
designReviewAgent |
milestone-driver:design-reviewer |
blockerResolverAgent |
milestone-driver:blocker-resolver |
uiSurfaceGlobs |
(absent → no design-lens review) |
sourceGlobs |
(pass through to the agent brief in Step 3) |
nonNegotiables |
(pass through to the agent brief in Step 3) |
domainSkills |
Expand before use: ${CLAUDE_PLUGIN_ROOT}/scripts/expand-domain-skills.{sh,ps1} ~/.claude/plugins/cache <entry>… (pwsh on Windows, bash elsewhere). Its stdout is what the Step 3 briefs carry, never the raw profile value; each unresolved: <entry> on stderr is named there as domainSkills unresolved: <entry>. Empty stdout is an absent key: the briefs omit domainSkills and still name those entries. |
projectDocs |
.project/ |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed 107c5fe2452b
- 9d ago First seen · 385 lines · 85 tokens per session scan A bdd448bbb6c1
triage is a skill published in the GitHub repository kenmulford/milestone-driver (2 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 8,687 once invoked, about $0.0004 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 skills, from other repositories
audit-round
External-audit role for arcgentic rounds. Loaded when arcgentic state.yaml is in awaitingaudit or auditinprogress, OR when the user explicitly requests an external audit of a finished round, OR when reviewing a handoff doc + commit chain against the round's declared scope. Produces a PASS / NEEDSFIX / AUDITINCOMPLETE…
review-pr
A pull-request review skill for evaluating proposed code changes and posting a quality verdict. A pull request is a request to merge changes into a shared codebase.
reconcile-docs
Best-effort reconciliation of the living architecture corpus against the code: the model reads docs/architecture/ plus the code and lists divergences with coordinates. Advisory only — an opinion of the model, never a verified verdict, no gates and no stamps. Nothing is applied automatically: corpus edits are a…
review
A read-only second opinion on a completed TASK, produced by another coding agent or by a separate clean-context review.
scout-consolidation
Launch a Scout consolidation session as a background process. Runs a lighter delta scan — captures what changed since the last run and updates action items and KB.
scout-briefing
Launch a Scout morning briefing session as a background process. Auto-detects mode (morning briefing, consolidation, or weekend briefing) from the current time and day.