escalation-governance SKILL.md skillA
escalation-governance from athola/claude-night-market is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add athola/claude-night-market/escalation-governance@git:20261023.bf6e922Pins git:20261023.bf6e922 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- athola/claude-night-market
- Path
plugins/abstract/skills/escalation-governance/SKILL.md- Versions recorded
- 9
- Latest version
- git:20261023.bf6e922, committed Oct 23, 2026
- First version recorded
- May 7, 2026
- Size
- 12,107 bytes
- Repository stars
- 348
- License
- MIT
Assess whether to escalate models. Use when evaluating reasoning depth.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Escalation Governance ## Overview Model escalation (haiku→sonnet→opus) trades speed/cost for reasoning capability. This trade-off must be justified. **Core principle:** Escalation is for tasks that genuinely require deeper reasoning, not for "maybe a smarter model will figure it out." ## The Iron Law ``` NO ESCALATION WITHOUT INVESTIGATION FIRST ``` Escalation is never a shortcut. If you haven't understood why the current model is insufficient, escalation is premature. ## When to Escalate **Legitimate escalation triggers:** | Trigger | Description | Example | |---------|-------------|---------| | Genuine complexity | Task inherently requires nuanced judgment | Security policy trade-offs | | Reasoning depth | Multiple inference steps with uncertainty | Architecture decisions | | Novel patterns | No existing patterns apply | First-of-kind implementation | | High stakes | Error cost justifies capability investment | Production deployment | | Ambiguity resolution | Multiple valid interpretations need weighing | Spec clarification | ## When NOT to Escalate **Illegitimate escalation triggers:** | Anti-Pattern | Why It's Wrong | What to Do Instead | …
Read the whole file at its exact version.
How to install
mdr add athola/claude-night-market/escalation-governance@sha256:839fb3fcc19e8d9aThe line at the top of this page pins the label git:20261023.bf6e922, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_wtr4ejeh22d3zmfg)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between May 7, 2026 and Oct 23, 2026, about one every 21 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261023.bf6e922 latest | 2026-10-23 | bf6e922 | 12,107 B | A | view · diff |
| git:20261021.ba0363b | 2026-10-21 | ba0363b | 12,056 B | A | view · diff |
| git:20261014.2769a9c | 2026-10-14 | 2769a9c | 11,754 B | A | view · diff |
| git:20260928.76a539b | 2026-09-28 | 76a539b | 12,062 B | A | view · diff |
| git:20260902.4a35d69 | 2026-09-02 | 4a35d69 | 11,579 B | A | view · diff |
| git:20260622.63c6c16 | 2026-06-22 | 63c6c16 | 12,452 B | A | view · diff |
| git:20260510.7d3c4b9 | 2026-05-10 | 7d3c4b9 | 11,856 B | A | view · diff |
| git:20260508.c09f147 | 2026-05-08 | c09f147 | 11,506 B | A | view · diff |
| v1.9.5 | 2026-05-07 | 29eb49d | 11,521 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12107 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
athola/claude-night-market · 348 stars · license MIT · pushed 2026-11-05 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_wtr4ejeh22d3zmfg GET https://markdownregistry.com/api/v1/resolve?ref=athola/claude-night-market/escalation-governance GET https://markdownregistry.com/api/v1/blob/839fb3fcc19e8d9a21ad5b4f3f2d825651b7ca33e6fc2244f95f1c9961ca03fd
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.