mcpbeat Sign in

Recall Reasoning Skill for Codex

Recall the reasoning behind a past change from Codex session history when available, falling back to commit diff and surrounding code. Use when the user asks to \"recall reasoning\", \"find reasoning\", \"look up reasoning\", \"recall implementation reasoning\", \"find the rationale\", \"why did I do X\", \"recall from transcripts\", or \"find the transcript for this commit\".

722 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
398
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/tobihagemann/turbo --skill recall-reasoning

The instruction itself

7 sections, as written by the author

Recall Reasoning

Recover the reasoning behind a change. Prefer Codex session history when it can be found; otherwise derive the explanation from git history and current code.

Inputs

Accept any of:

  • A commit SHA
  • A file path, optionally with a line number (<path>:<line>)
  • A reviewer question plus surrounding context

If only a file is given, use git blame to resolve the commit that last touched the line.

Step 1: Resolve the Commit

Resolve the target commit:

git rev-parse <sha>
git blame -L <line>,<line> -- <path>

Collect the commit subject, changed files, and relevant diff:

git show --stat --oneline <sha>
git show -- <path>

Step 2: Search Codex Session History

If Codex session files are available, search them for the commit SHA, touched file paths, branch name, and distinctive user request text:

Write the patterns to a file with apply_patch, one per line, then match them literally:

rg -F -f <pattern-file> ~/.codex/sessions

-F is required, not just safer: an unescaped $ inside request text is a regex anchor and silently drops the match.

Read only the smallest relevant transcript excerpts. Prefer sessions close to the commit time and sessions that mention both the file and the task.

If no matching session is found, continue with the fallback path.

Step 3: Synthesize

If session reasoning was found:

  • Lead with the why. The diff already shows the what.
  • Quote or paraphrase only the relevant reasoning.
  • Keep the explanation to one or two paragraphs.

If no session reasoning was found:

  • Read the commit diff and surrounding current code.
  • Infer the most likely rationale from the code, tests, plan/spec artifacts, and PR context.
  • Mark the output as fallback-derived.

Step 4: Output

When session reasoning was found:

**Commit:** <short-sha> — <subject>
**Session:** <session reference>

<one or two paragraphs of reasoning>

When no session reasoning was found:

**Commit:** <short-sha> — <subject>
**Session:** none found

<fallback explanation derived from git history and current code>

Then call update_plan to mark this step completed and continue with the next step of the active workflow.

Rules

  • Treat session excerpts as evidence, not ground truth.
  • Do not read full transcript files unless excerpts are insufficient.
  • If current code contradicts a remembered rationale, note the discrepancy.

Other skills for the same job

different authors, same section of the catalogue
Git Commit
by github
vendor ×3

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

799 tokens
Github Code Review
by ComeOnOliver
×3

Comprehensive GitHub code review with AI-powered swarm coordination

13k tokens
Commit Work
by softaworks
×2

Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.

2k tokens
Verification & Quality Assurance
by Microck
×2

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

4k tokens
Gh CLI
by christophacham
×2

GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.

10k tokens
Github
by Dicklesworthstone
×2

GitHub CLI - manage repositories, issues, pull requests, actions, releases, and more from the command line.

1k tokens
Codebase Cleanup Refactor Clean
by ComeOnOliver
×2

You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.

9k tokens
Codebase Cleanup Tech Debt
by ComeOnOliver
×2

You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti

6k tokens

How to use it

Copy the folder

Take tobihagemann/turbo-recall-reasoning from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.