Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/runxhq/runxnpx agentmods add skills/runxhq/runx/incident-commanderWrote 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/runxhq/runx/incident-commander)<a href="https://agentmods.dev/skills/runxhq/runx/incident-commander"><img src="https://agentmods.dev/badge/skills/runxhq/runx/incident-commander/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/runxhq/runx/incident-commander"><img src="https://agentmods.dev/badge/skills/runxhq/runx/incident-commander.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 55 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00030 | $0.01187 |
| Opus 5 | $0.00015 | $0.00593 |
| Sonnet 5 | $0.00006 | $0.00237 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
incident-commander 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 6d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Commander
Use this skill for one command decision inside an incident that already belongs
to a Runx agency case. It checks the folded case and fixed roster, asks the
canonical ops-desk skill for one bounded decision, then enforces the incident
rules before returning incident_turn.
The result is one bounded, receipt-backed command turn: an exact dispatch, approval escalation, verified resolution from a supplied member receipt, or actionable blocker. This skill does not append an agency event, acquire a case lease, send a message, call a provider, or close external state. The agency driver remains responsible for the expected-version append and for binding this run's sealed receipt to the case stream.
Composes
ops-desk#advance
Required context
Supply case_id, driver_id, incident_objective, folded case_state, and a
fixed roster. The objective must be one of begin, assign, send,
resolve, or postmortem.
The roster has exactly three entries:
commander, which normally namesops-deskand its incident command scope;responder_lead, which names the response skill and its allowed scope;comms_lead, which namessend-asorslack-notifyand its allowed scope.
Each entry includes a principal, skill, and nonempty scope ceiling. Roles and
principals must be unique. An assign turn also needs case_state.named_owner
to match one roster role or principal.
case_state is a bounded projection, not the incident event history. Durable
history stays behind the agency data source. Include declaration status,
severity, scope, current turn, and only the evidence or pending decision needed
for this command turn.
Communications
A send starts from case_state.pending_escalation.proposed_handoff. That object
binds the exact comms_lead principal, send-as or slack-notify, runner
plan, channel, audience, and SHA-256 content digest.
What ships with it
5 files 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.
- 6d ago First seen · 122 lines · 30 tokens per session scan A f0cf1babd164
incident-commander is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 1,187 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 2026-09-03.
Other skills, from other repositories
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.