New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Codex Analyze Session

by tbhb in tbhb/vale-ai-tells

Query a Codex transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends.

MITAuto-check passedProduct & Project Management

Install Codex Analyze Session

skills CLI
$ npx skills add tbhb/vale-ai-tells --skill codex-analyze-session -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install tbhb/vale-ai-tells codex-analyze-session --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/tbhb/vale-ai-tells.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/codex-analyze-session .claude/skills/codex-analyze-session && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
codex-analyze-session
GitHub stars
115
Token cost
~1.4k tokens
SKILL.md length
748 words
Files
11 (incl. scripts, references)
Skills in repo
27
Repo updated
First seen
Licence
MIT

At a glance

Query a Codex transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends.

  • Works in 6 steps: open the task list → read the lines the preflight listed → test the session's own conclusions → …
  • The user asks for a retrospective on a past session
  • SKILL.md covers Which session, Preflight, Step 0: open the task list and Step 1: read the lines the…, plus 5 more sections
  • Runs Shell and Python scripts from its folder; calls bash

What it does

Codex Analyze Session is an agent skill from tbhb/vale-ai-tells. Query a Codex transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends. The tool reads the file line by line and reports every failure and repeated tool call by line number. Use this skill when the user asks for a retrospective on a past session, or hands over a transcript path with a question about it.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts and reference files (for example `references/FIX_SURFACES.md`, `references/LOCATE_SESSION.md` and `references/SESSION_CLI.md`).

It sits in Product & Project Management, covering Retrospectives. The repository describes itself as: In today's rapidly evolving landscape, vale-ai-tells is a comprehensive, cutting-edge Vale style package that empowers writers to seamlessly delve into the rich tapestry of AI…. The licence is MIT.

When your agent uses it

  • The user asks for a retrospective on a past session
  • Hands over a transcript path with a question about it

Example prompts

  • “/codex-analyze-session”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. open the task list
  2. read the lines the preflight listed
  3. test the session's own conclusions
  4. verify every figure with three agents
  5. recommend fixes across the five areas
  6. write the retrospective

What it can do on your machine

Read from SKILL.md and the folder at commit 4c7abc9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 3 files in scripts/ (Shell and Python), which the agent can run.

    Shell commands in SKILL.md call:

    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codex Analyze Session loads about 1.4k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 748 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from tbhb/vale-ai-tells at commit 4c7abc9, republished under its MIT licence (© tbhb). 748 words, ~1,394 tokens.

Download SKILL.mdSave it as .claude/skills/codex-analyze-session/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
codex-analyze-session
description
Query a Codex transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends. The tool reads the file line by line and reports every failure and repeated tool call by line number. Use this skill when the user asks for a retrospective on a past session, or hands over a transcript path with a question about it.

Analyze a session

Work the steps in order. This skill ends once the retrospective exists on disk and the operator has its path. Acting on what it recommends is separate work. Use the codex-commit skill for any change that comes out of it.

Which session

Use the absolute transcript path from the user's request. A bare session ID also works when it names exactly one file under ~/.codex/sessions/.

If the user gives neither, preflight explains how to find a session. Spawn a fresh delegated agent with fork_turns: "none". Run preflight again with the path it returns. Never load session files into model context merely to locate one because the locator can stream them.

Preflight

Run bash .agents/skills/codex-analyze-session/scripts/preflight.sh <path-or-id> and read its report.

Step 0: open the task list

Create these tasks with update_plan, then move each to in_progress and completed as you go. They're the checklist the rest of this document expands.

  1. Read the lines the preflight listed
  2. Test the session's own conclusions
  3. Verify every figure with three agents
  4. Recommend fixes across the five areas
  5. Write the retrospective

Stop before any of it where preflight couldn't resolve the transcript, or reports a missing precondition. Say what's wrong and hand back.

The preflight already resolved the transcript and summarized the session. It created the retro directory at <main worktree>/.codex/retros/YYYYMMDD_<session ID>/ and copied the evidence into it. Read that report before forming any hypothesis, because it writes everything it prints to artifacts/ as well, where a later reader can check it.

.agents/skills/codex-analyze-session/references/SESSION_CLI.md documents every subcommand, for when a report needs more detail than the preflight printed.

Step 1: read the lines the preflight listed

The preflight listed the failing lines and the line ranges of each repeated sequence. Open those, and nothing else:

text
.agents/skills/codex-analyze-session/scripts/session.py grep <transcript> 'pattern' --context 300
.agents/skills/codex-analyze-session/scripts/session.py show <transcript> 361,408,1938

grep searches the decoded content blocks, so what prints matches what the model saw. Add --kind THINK to read what the agent believed at the time, which is often where an error begins. show prints whole records, once a report has given you a specific line number.

Step 2: test the session's own conclusions

A transcript records what an agent believed, which isn't always what was true. Treat every claim in it as a hypothesis with a line number attached, including the agent's own corrections.

Re-run the decisive command wherever that environment still exists.

Check that a test can fail before trusting a result of zero. A test returning nothing may mean the thing is absent, or may mean the test stopped examining anything. Give it a case that must produce output, and treat an empty result as evidence only after that check passes. A test that has stopped examining anything reports nothing whatsoever, where a working one still returns unrelated findings alongside the empty answer.

Show full SKILL.md (286 more words)Show less

Step 3: verify every figure with three agents

Readers trust a number more than a description, so a wrong count does more damage than a wrong impression. No figure reaches the operator without independent replication.

Follow .agents/skills/codex-analyze-session/references/VERIFY_FIGURES.md. It gives the claims table format, the prompt each verifier receives, the isolation rule for verifiers that write files, and how to settle a figure they disagree on.

Hold every figure until all three report. A verifier that hasn't answered yet isn't an abstention, and counting it as one discards the report most likely to disagree.

Step 4: recommend fixes across the five areas

Step 3 runs identical prompts, because replication gains nothing from a division of labor. This step does the opposite, giving each agent one area so the recommendations stay distinct.

Follow .agents/skills/codex-analyze-session/references/FIX_SURFACES.md. It names the five areas, the shared prompt, and the block each agent receives.

Synthesize the results yourself. Each agent sees one area, while this session has the verified figures and the full set of findings that no agent had alone.

Step 5: write the retrospective

Fill in the RETRO.md the preflight created, following .agents/skills/codex-analyze-session/references/WRITING_THE_RETRO.md.

Cite a line number for every claim. Rank findings by round trips wasted rather than by how irritating they were. State what each fix costs as well as what it improves, and give the operator the retro path when you report back.

Preconditions

This skill assumes the shared tbhb toolchain:

  • uv on PATH, which the session.py shebang uses to select an interpreter
  • a git repository, because the retro directory resolves from the main checkout
  • a transcript path or session ID naming exactly one file

Preflight checks each. Where one is missing, tell the operator rather than improvising a substitute.

© tbhb, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (scripts, references) in .claude/skills/codex-analyze-session of tbhb/vale-ai-tells.

  • SKILL.md
  • references/FIX_SURFACES.md
  • references/LOCATE_SESSION.md
  • references/SESSION_CLI.md
  • references/VERIFY_FIGURES.md
  • references/WRITING_THE_RETRO.md
  • scripts/new-retro.sh
  • scripts/preflight.sh
  • scripts/session.py
  • templates/RETRO.md
  • tokens.json

Open the folder on GitHubat commit 4c7abc9

Compare with similar skills

Codex Analyze Session next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codex Analyze Session compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codex Analyze Session this skilltbhb/vale-ai-tells115—~1.4kAutomated safety check: PassMIT
Weekly Engineering Retrogarrytan/gstack136k—~2.4kAutomated safety check: PassMIT
Dough Execute Planterryyin/lizard2.5k—~4.3kAutomated safety check: PassCustom licence
After Action Reportrampstackco/claude-skills9401 repos~2.5kAutomated safety check: PassMIT
Oral Paper SkillAdkid-Zephyr/oral-paper-skill340—~1.9kAutomated safety check: PassNone
Deck Retroasheshgoplani/agent-deck1k—~1.8kAutomated safety check: PassMIT

Similar skills

  • Weekly Engineering Retro

    garrytan/gstack

    Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.

    136k GitHub stars~2.4k tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Dough Execute Plan

    terryyin/lizard

    Executes one selected story or bounded retrospective correction through an executable plan, or one authorized planless slice from a selected simple story or a contextual instruction, with…

    2.5k GitHub stars~4.3k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

  • After Action Report

    rampstackco/claude-skills

    Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons.

    940 GitHub starsUsed in 1 repo~2.5k tokens
    Product & Project ManagementAuto-check passed

  • Oral Paper Skill

    Adkid-Zephyr/oral-paper-skill

    Help authors learn from exemplary ICLR, ICML, and NeurIPS papers through source-linked manuscript comparisons, concrete writing and experiment suggestions, and guided reflection.

    340 GitHub stars~1.9k tokensUpdated 20 days ago
    Product & Project ManagementAuto-check passed

  • Deck Retro

    asheshgoplani/agent-deck

    Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs.

    1k GitHub stars~1.8k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed

  • Dough Execution Retrospective

    terryyin/lizard

    Reviews planned, completed planless quick, or quick-to-planned execution against original intent, aggregate commits, current whole-product architecture, and tests, including after cleanup.

    2.5k GitHub stars~4k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed

More from tbhb/vale-ai-tells

All 27 skills in this repo

  • Analyze Session

    tbhb/vale-ai-tells

    Query a Claude Code transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends.

    115 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Codex Fix PR

    tbhb/vale-ai-tells

    Diagnose failing pull request checks, reproduce them locally, make focused fixes, commit them through codex-commit, and refresh the published description when needed.

    115 GitHub stars~575 tokensUpdated today
    Auto-check passed

  • Codex Merge PR

    tbhb/vale-ai-tells

    Squash merge a pull request. An agent skill from tbhb/vale-ai-tells.

    115 GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Codex PR

    tbhb/vale-ai-tells

    Open or update a pull request for the current branch with an independently drafted and reviewed PRAGENTDESC.md.

    115 GitHub stars~846 tokensUpdated today
    Auto-check passed

  • Codex Rebase

    tbhb/vale-ai-tells

    Replay the current branch onto its base and establish that the result is sound.

    115 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Codex Resolve Rebase Conflicts

    tbhb/vale-ai-tells

    Settle the conflicts a merge-backend rebase left behind. An agent skill from tbhb/vale-ai-tells.

    115 GitHub stars~2.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Codex Analyze Session

What does Codex Analyze Session do?

Query a Codex transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends. Codex Analyze Session is an agent skill from tbhb/vale-ai-tells. Query a Codex transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends.

When should I use Codex Analyze Session?

Codex Analyze Session fits situations like: the user asks for a retrospective on a past session; hands over a transcript path with a question about it.

How do I install Codex Analyze Session in Claude Code?

Run `npx skills add tbhb/vale-ai-tells --skill codex-analyze-session -a claude-code`. Or copy the skill folder (.claude/skills/codex-analyze-session in tbhb/vale-ai-tells) into .claude/skills/codex-analyze-session in your project. Claude Code loads it when a task matches its description.

How do I install Codex Analyze Session in Codex?

Run `npx skills add tbhb/vale-ai-tells --skill codex-analyze-session -a codex`. Or copy the skill folder (.claude/skills/codex-analyze-session in tbhb/vale-ai-tells) into .agents/skills/codex-analyze-session in your project. Codex loads it when a task matches its description.

Can I use Codex Analyze Session in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tbhb/vale-ai-tells --skill codex-analyze-session -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codex-analyze-session, .gemini/skills/codex-analyze-session, .github/skills/codex-analyze-session and .opencode/skills/codex-analyze-session in your project.

What does Codex Analyze Session need to run?

Going by SKILL.md and its folder, Codex Analyze Session needs a shell and Python for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: Python 3; A Bash shell.

Does Codex Analyze Session access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Codex Analyze Session safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Codex Analyze Session use?

Codex Analyze Session is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codex Analyze Session use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4k tokens, read only when the agent opens those files.

What are the alternatives to Codex Analyze Session?

Skills that share tags, products or a category with Codex Analyze Session: Weekly Engineering Retro (garrytan/gstack, 136k stars), Dough Execute Plan (terryyin/lizard, 2.5k stars), After Action Report (rampstackco/claude-skills, 940 stars) and Oral Paper Skill (Adkid-Zephyr/oral-paper-skill, 340 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codex Analyze Session?

tbhb (a GitHub user) maintains it in tbhb/vale-ai-tells, which has 115 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on October 7, 2026.

Source: tbhb/vale-ai-tells on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.