SKILLEMALL.ai
GitHub ↗ RU Sign in

BC read-codex-history

Reads, searches and exports local OpenAI Codex history without continuing work: session inventory, timelines, verbatim user input, indexed search, and rollout identity/fork lineage. Use when the user asks what they told Codex, wants a Session ID, or evidence of what a run did. Not for Claude Code (use read-claude-code-history); with no platform named, start at local-conversation-history.

daymade/claude-code-skills Claude Code author: daymade MIT 39 files · 31 scripts body ≈ 7 123 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Reads, searches and exports local OpenAI Codex history without continuing work: session inventory, timelines, verbatim user input, indexed search, and rollout…

As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

AnalyzerSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
92/100
safety, quality, tests
Safety 60%
96
Quality 40%
85
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 4

✓ No critical or high findings

Medium and low: 4
  • low Secrets in code secret-high-entropy-token references/codex_rollout_format.md:203
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    parent = directory / f"roll…00-{root_id}.jsonl"
    quoted
  • low Secrets in code secret-high-entropy-token references/codex_rollout_format.md:207
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    leaf = directory / f"roll…00-{root_id}_{child_id}.jsonl"
    quoted
  • low Secrets in code secret-high-entropy-token references/codex_rollout_format.md:223
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    legacy = directory / f"roll…00-{child_id}.jsonl"
    quoted
  • low Secrets in code secret-high-entropy-token references/codex_rollout_format.md:235
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    copied = directory / f"roll…00-{child_id}.jsonl"
    quoted

Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7123 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 83, 433, 438): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 63/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 7 mutating operations with no state check
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70Execution cost. Instruction body is 7123 tokens
  • 100Steps. 37 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (3 tags): a typed call is more reliable
  • medium 6 test cases, all positive: not one "should refuse" or "should ask first"
  • low No test case covers injection arriving through data

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 390: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 37 items
  • +4Has examples (11 code blocks)
  • +4Reference files are cited in the instructions (6 of 6)
  • +3All 7 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.