Recall Reasoning
- 518 installs
- 3.9k repo stars
- Updated January 26, 2026
- parcadei/continuous-claude-v3
recall-reasoning is a Claude Code skill that searches past agent sessions across artifact indexes and reasoning files for developers who need prior decisions, successes, and failures without re-deriving context.
About
recall-reasoning is an agent-memory skill from continuous-claude-v3 that queries two sources: an Artifact Index of handoffs, plans, and ledgers with post-mortems, and Reasoning Files capturing build attempts, test failures, and commit context. Developers invoke it when starting work similar to a prior session, debugging a recurring issue, or asking what was tried last time with a component or API. The skill is user-invocable false, so agents load it when similarity or history questions appear. recall-reasoning complements grep and git log by surfacing explicit reasoning chains and documented what-worked versus what-failed patterns across long multi-day agent runs.
- Forces explicit recall of previous conclusions before generating new responses
- Reduces context drift and repetitive AI loops in extended coding sessions
- Works automatically as part of the Continuous Claude v3 workflow
- Improves reasoning quality across multi-hour agent projects
Recall Reasoning by the numbers
- 518 all-time installs (skills.sh)
- +3 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #1,736 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill recall-reasoningAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 518 |
|---|---|
| repo stars | ★ 3.9k |
| Last updated | January 26, 2026 |
| Repository | parcadei/continuous-claude-v3 ↗ |
How do agents recall past reasoning across long sessions?
Maintain coherent context and explicit reasoning across long agent sessions without losing thread or repeating prior conclusions.
Who is it for?
Developers running multi-session Claude Code workflows who need explicit recall of prior decisions and post-mortems.
Skip if: Greenfield tasks with no prior session artifacts or teams that only need one-shot code generation without historical context.
When should I use this skill?
A developer asks what was done last time, why a decision was made, or whether a prior approach failed for the same issue.
What you get
Matched handoffs, plans, ledgers, build-attempt notes, and commit-context excerpts with worked versus failed patterns.
- Relevant prior decisions
- Worked and failed approach summaries
Files
Recall Past Work
Search through previous sessions to find relevant decisions, approaches that worked, and approaches that failed. Queries two sources:
1. Artifact Index - Handoffs, plans, ledgers with post-mortems (what worked/failed) 2. Reasoning Files - Build attempts, test failures, commit context
When to Use
- Starting work similar to past sessions
- "What did we do last time with X?"
- Looking for patterns that worked before
- Investigating why something was done a certain way
- Debugging an issue encountered previously
Usage
Primary: Artifact Index (rich context)
uv run python scripts/core/artifact_query.py "<query>" [--outcome SUCCEEDED|FAILED] [--limit N]This searches handoffs with post-mortems (what worked, what failed, key decisions).
Secondary: Reasoning Files (build attempts)
bash "$CLAUDE_PROJECT_DIR/.claude/scripts/search-reasoning.sh" "<query>"This searches .git/claude/commits/*/reasoning.md for build failures and fixes.
Examples
# Search for authentication-related work
uv run python scripts/core/artifact_query.py "authentication OAuth JWT"
# Find only successful approaches
uv run python scripts/core/artifact_query.py "implement agent" --outcome SUCCEEDED
# Find what failed (to avoid repeating mistakes)
uv run python scripts/core/artifact_query.py "hook implementation" --outcome FAILED
# Search build/test reasoning
bash "$CLAUDE_PROJECT_DIR/.claude/scripts/search-reasoning.sh" "TypeError"What Gets Searched
Artifact Index (handoffs, plans, ledgers):
- Task summaries and status
- What worked - Successful approaches
- What failed - Dead ends and why
- Key decisions - Choices with rationale
- Goal and constraints from ledgers
Reasoning Files (.git/claude/):
- Failed build attempts and error output
- Successful builds after failures
- Commit context and branch info
Interpreting Results
From Artifact Index:
✓= SUCCEEDED outcome (pattern to follow)✗= FAILED outcome (pattern to avoid)?= UNKNOWN outcome (not yet marked)- Post-mortem sections show distilled learnings
From Reasoning:
build_fail= approach that didn't workbuild_pass= what finally succeeded- Multiple failures before success = non-trivial problem
Process
1. Run Artifact Index query first - richer context, post-mortems 2. Review relevant handoffs - check what worked/failed sections 3. If needed, search reasoning - for specific build errors 4. Apply learnings - follow successful patterns, avoid failed ones
No Results?
Artifact Index empty:
- Run
uv run python scripts/core/artifact_index.py --allto index existing handoffs - Create handoffs with post-mortem sections for future recall
Reasoning files empty:
- Use
/commitafter builds to capture reasoning - Check if
.git/claude/directory exists
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Pick recall-reasoning over git blame when you need documented reasoning and post-mortems, not just line-level authorship.
FAQ
What sources does recall-reasoning search?
recall-reasoning queries two sources: an Artifact Index with handoffs, plans, and ledgers plus post-mortems, and Reasoning Files with build attempts, test failures, and commit context from prior sessions.
When should recall-reasoning load automatically?
recall-reasoning loads when a developer starts similar past work, asks what was done last time, hunts patterns that worked, or debugs an issue encountered in an earlier session.