ychampion/cskill-agents/exact-rendered-decision-journaling
Claude Code and agent skill by ychampion/cskill-agents
- community
Checking that the SKILL.md file is still in the repository.
Journal each per-message tool result replacement so resume logic replays the exact preview the model saw.
Install
npx vskill@latest install ychampion/cskill-agents/exact-rendered-decision-journalingSKILL.md
SKILL: Exact Rendered Decision Journaling
Domain: tool-orchestration Trigger: Apply whenever per-message budgeting rewrites tool_result content so transcripts capture the preview string and resume logic can reapply the same decisions. Source Pattern: Distilled from reviewed tool-loop and result-shaping patterns.
Core Method
After enforceToolResultBudget persists a candidate, produce a ToolResultReplacementRecord (kind: 'tool-result', toolUseId, replacement) that stores the literal preview returned by buildLargeToolResultMessage. Pass newlyReplaced to the writeToTranscript callback so every replacement is serialized in the conversation transcript; later, reconstructContentReplacementState(messages, records, inheritedReplacements) can rebuild the same seenIds/replacements map, and provisionContentReplacementState gates the feature flag (tengu_hawthorn_steeple) so journaling stays optional.
Key Rules
- Persist the exact preview string the model consumed—the replacement record must not approximate or trim the visible content, or prompt-cache alignment breaks.
- Include
toolUseIdwith each record so resume enforcement can quickly look up replacements without re-running persistence. - Forward
parentState.replacementsintoreconstructForSubagentResumewhen resuming forks so inherited decisions reapply exactly. - Guard
writeToTranscript; it may be undefined in ephemeral contexts, so only call it when provided. - When the flag is disabled,
provisionContentReplacementStateshould returnundefinedand journaling remains inert.
Example Application
In the query loop pass the transcript writer to applyToolResultBudget; the callback serializes newlyReplaced records, which are later replayed by provisionContentReplacementState(initialMessages, records) during resume so the budget enforces the same replacements it originally made.
Anti-Patterns (What NOT to do)
- Do not journal before
persistToolResultsucceeds and the preview is built—the replacement string must exist before you write it down. - Do not drop
kind: 'tool-result'or thetoolUseIdfields;reconstructContentReplacementStaterelies on them to filter and lookup. - Avoid journaling duplicates (e.g., from re-applied replacements); only persist what is new so transcripts stay minimal.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/exact-rendered-decision-journaling/SKILL.md
Popularity
- Repository stars
- 36
- Repository forks
- 7
- 7-day trend score
- 18
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ychampion/cskill-agents/exact-rendered-decision-journaling)