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/HoangNguyen0403/agent-skills-standardWrote 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/hoangnguyen0403/agent-skills-standard/incident-hotfix)<a href="https://agentmods.dev/commands/hoangnguyen0403/agent-skills-standard/incident-hotfix"><img src="https://agentmods.dev/badge/commands/hoangnguyen0403/agent-skills-standard/incident-hotfix/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/hoangnguyen0403/agent-skills-standard/incident-hotfix"><img src="https://agentmods.dev/badge/commands/hoangnguyen0403/agent-skills-standard/incident-hotfix.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 | $0.00023 | $0.00578 |
| Opus 5 | $0.00012 | $0.00289 |
| Sonnet 5 | $0.00005 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
incident-hotfix 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Hotfix Workflow
Goal: Stop user-facing harm immediately, then hand off to root-cause discipline instead of debugging live.
Steps
- Triage:
- Severity, blast radius, affected environments/markets, and whether the regression is a rollback candidate.
- Load
deploy-releaserollback path and prior deployment report if present.
- Mitigate first:
- Prefer rollback, feature flag disable, or config revert over a live code fix.
- Confirm mitigation stopped user-facing harm before investigating root cause.
- Do not attempt a root-cause code fix under live production pressure.
- Stabilize:
- Monitor logs, metrics, errors, and core user flows until signals return to baseline.
- Record mitigation timestamp, owner, and evidence.
- Route to remediation:
- Once stable, hand off to
dev-fixfor root-cause debugging under the normal Propose -> Approve -> Verify cycle. - Do not skip
dev-fix's root-cause-before-code requirement just because mitigation already shipped.
- Once stable, hand off to
- Route to learning:
- After
verify-workconfirms the permanent fix, route toretro-learnfor a postmortem.
- After
Runtime Contract
- Use only for production incidents or urgent regressions with active user-facing harm; non-urgent bugs go directly to
dev-fix. - Required inputs: incident signal (alert, report, or error spike) plus a mitigation path (rollback, flag, or config revert).
- Return BLOCKED only when no mitigation path exists and the incident cannot be safely stopped.
Handoff Payload
slug,operator_profile(carried, not re-inferred), severity, mitigation applied, stabilization evidence, outcome report, next workflow.
Blocking Questions
- Ask max 3 at a time with a recommended default and 2-3 options.
Output Template
# Incident Hotfix: [Name]
## Severity And Blast Radius
## Mitigation Applied
## Stabilization Evidence
| Signal | Before | After |
| --- | --- | --- |
| [signal] | [value] | [value] |
## Root Cause Handoff
## Outcome Report
feature_status: partially_implemented | blocked
requirement_trace: BRD-OBJ-* -> REQ-* -> AC-* -> SRS-* -> evidence
completed_evidence: []; missing_evidence: []; decision_needed: []; recommended_next_workflow: dev-fix
## Next Workflow
dev-fix | verify-work | retro-learn
## Cost Report
Call `get_session_cost(workflow="incident-hotfix")` before final handoff.
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 · 64 lines · 23 tokens per session scan A a3454a24769e
incident-hotfix is a command published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 578 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 2026-09-06.
Other commands, from other repositories
debug
Structured bug diagnosis and fixing workflow that reproduces, diagnoses root cause, applies a minimal fix, writes regression tests, and scans for similar patterns.
incident
An incident-response assistant for guiding work when a software service has a serious failure or disruption.
ralph
Ralph - persistent self-referential execution loop wrapping ultrawork with a spawned independent judge.
validate
Run SDLC compliance check against the current project. Validates build system, code quality, testing, CI/CD, security, documentation, VCS, and release configurations.
e2e
An end-to-end testing assistant for guiding tests that exercise a complete user flow across an application. E2E tests check the system as a user would use it, rather than checking one small part in isolation.
journey-test
The /journey-test command turns a project description into a coherent user journey test plan (TESTPLAN-NNN.md) plus matching E2E skeletons, so a new project has a complete, ordered test journey from day one.