hjemmesidekongen/reasoning-trace-optimizer
plugins/kronen/skills/reasoning-trace-optimizer/SKILL.md
Analyzes agent reasoning patterns in trace-light.log to detect context degradation, tool confusion, instruction drift, goal abandonment, circular reasoning, and premature conclusions. Produces a diagnosis with specific patterns found and a fix recommendation. Use when an agent session is underperforming, when repeated tool calls aren't making progress, when an agent seems to have lost track of its goal, when debugging why a plan stalled or looped, or when reviewing a completed session for quality issues.
tools
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai reasoning-trace-optimizerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 10:04 AM2.6s1 file scanned
SKILL.md
- name:
- reasoning-trace-optimizer
- description:
- >
- user_invocable:
- false
- interactive:
- false
- depends_on:
- []
- type:
- data_validation
- - name:
- actionable_output
- verify:
- Each finding includes a specific fix recommendation
- fail_action:
- Add concrete fix for every pattern found — no bare problem reports
- on_fail:
- Complete all pattern checks and write diagnosis file before finishing.
- on_pass:
- Diagnosis complete. Findings written to .ai/traces/reasoning-diagnosis.md.
- model_tier:
- senior
- origin:
- kronen
- inspired_by:
- Agent-Skills-for-Context-Engineering-main — interleaved-thinking skill
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- Adapted pattern detection methodology to trace-light.log format. Added 6-category degradation taxonomy and fix recommendations.
reasoning-trace-optimizer
Diagnoses agent reasoning quality by scanning trace-light.log for structural failure patterns. Surfaces what went wrong and how to fix it.
When to run
- After a session that didn't complete its goal
- When a plan stalled and the cause is unclear
- When reviewing a session to extract improvement patterns
- Before running instinct-extractor on a suspicious session
6 Pattern Categories
See references/process.md for full detection criteria and fix recommendations.
| Pattern | Signal | Severity | |---------|--------|---------| | Context degradation | Repeated reads of same files, increasing error rate | high | | Tool confusion | Wrong tool for task, tool retries without adaptation | medium | | Instruction drift | Actions diverging from original task description | high | | Goal abandonment | Task incomplete, agent stops without explicit block | critical | | Circular reasoning | Same investigation steps repeated 2+ times | medium | | Premature conclusion | Claimed done before verification-gate ran | high |
Output
Writes references/process.md-defined diagnosis to .ai/traces/reasoning-diagnosis.md.
Related Skills
hjemmesidekongen/brand-strategy
development
VerifiedTrustedCommunity
Creates a brand from scratch through market research and interactive sparring. Runs competitive research via Perplexity, then guides the user through positioning, audience, voice, values, and content pillars. Produces the full brand guideline set at .ai/brand/{name}/. Use when building a new brand, defining brand strategy for a product, or when /våbenskjold:create is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-loader
testing
VerifiedTrustedCommunity
Loads brand guidelines from .ai/brand/{name}/ and makes them available to the current context. Progressive disclosure: L1 confirms brand exists, L2 loads summary, L3 loads specific files on demand. Use when a downstream skill or user needs brand context, or when /våbenskjold:apply is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-evolve
documentation
VerifiedTrustedCommunity
Guided reinvention of an existing brand guideline. Loads current brand from .ai/brand/{name}/, identifies what to keep vs change, and walks the user through targeted evolution. Preserves brand equity while updating positioning, voice, or values. Use when refreshing a brand or when /våbenskjold:evolve is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-audit
development
VerifiedTrustedCommunity
Codifies an existing brand from materials, samples, and references. Analyzes provided content to extract voice patterns, values, and positioning. Produces the same guideline format as brand-strategy. Use when a brand already exists but isn't documented, or when /våbenskjold:audit is invoked.
SKILL.mdUpdated Apr 5, 2026