night-market-model-and-harness-updates

Featured

Sweep plugins, skills, agents, commands, and hooks after a model release or Claude Code version bump. Use when upstream ships. Do not use for routine edits; use night-market-change-control.

AI & Automation 337 stars 34 forks Updated today MIT

Install

View on GitHub

Quality Score: 88/100

Stars 20%
84
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Night Market Model and Harness Updates When Anthropic ships a model or Claude Code ships a version, the pins scattered through this repo rot silently. This skill runs the sweep that finds the rot, researches what actually changed, applies the updates, and records where upstream stood so the next run reports only the new delta. The watermark is the point. Without it every audit restarts from zero and re-derives the same answer by hand. `.claude/upstream-baseline.json` holds the last recorded upstream state, and each run diffs against it. ## When to run | Trigger | Signal | |---------|--------| | Model release | A tier or model ID ships that the ledger does not record | | Harness release | `claude --version` differs from the ledger | | Scheduled check | Monthly, to catch a release nobody noticed | ## The five steps Run them in order. Each one gates the next. ```bash # 1. Detect. Deterministic, no model in the loop. python3 scripts/check_upstream_drift.py # 2. Research what changed (only when step 1 reports drift). # Release notes and model cards are mandatory sources. # 3. Map findings onto asset classes. # 4. Sweep the implicated classes. # 5. Prove, then record the new watermark. python3 scripts/check_upstream_drift.py && \ python3 scripts/check_agent_model_matrix.py ``` Step 5 runs before the ledger is written, never after. Recording a migration that has not passed its proof is the failure the ledger exists to prevent. ## What the detector proves and what i...

Details

Author
athola
Repository
athola/claude-night-market
Created
9 months ago
Last Updated
today
Language
Python
License
MIT

Integrates with

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

refreshing-anthropic-guidance

Sweeps the local Claude Code harness — agents, skills, hooks, rules, workflows, CLAUDE.md — against Anthropic's current guidance/models, diffs last-verified state, plans remediation. Use for /refreshing-anthropic-guidance, "is our harness up to date with Anthropic", "model pins current". Distinct from researching-anthropic-guidance and auditing.

0 Updated today
monte3l
AI & Automation Listed

refresh-models

Review and update the choosing-models tier data. Run /refresh-models to detect lineup drift against the platform's current model list, read the release notes, and produce a reviewable changeset (models.toml lineup edits plus any guidance edits) for approval. Mechanical lineup changes are applied on approval; threshold and doctrine edits are never auto-applied without calibration evidence. Manual-only.

2 Updated 5 days ago
grimaldost
AI & Automation Listed

unhobble

Empirical bare-baseline experiment on a repo's standing instructions: reversibly strip project CLAUDE.md/rules/behavioral hooks/skills on a dedicated branch, work normally against the bare model logging observed stumbles to a ledger, then re-add ONLY instructions with repeated same-cause evidence, each restore citing its ledger rows. Measures the model where sibling audit-instructions judges the text. Use when: 'unhobble', 'run the bare experiment', 'delete my CLAUDE.md and see', 'does the model still need these instructions', 'new model dropped, re-baseline', 'instruction ablation experiment'. Human-gated mutations; resumable state.

16 Updated today
melodic-software