Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jdpalumbo2/workbench --skill clodexgit clone --depth 1 https://github.com/jdpalumbo2/workbenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jdpalumbo2/workbench/clodex)<a href="https://agentmods.dev/skills/jdpalumbo2/workbench/clodex"><img src="https://agentmods.dev/badge/skills/jdpalumbo2/workbench/clodex/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jdpalumbo2/workbench/clodex"><img src="https://agentmods.dev/badge/skills/jdpalumbo2/workbench/clodex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.13087 |
| Opus 5.5 | $0.00034 | $0.05235 |
| Sonnet 5.5 | $0.00017 | $0.02617 |
| Haiku 4.5 | $0.00009 | $0.01309 |
Grade A, and why
clodex scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 919 lines — stays where its author put it; the contents beside it link to each section on GitHub.
clodex — the front door
Overview
One entry point for all work, so nobody has to remember stage names. This skill runs five things in order and then hands off:
- Preflight — prove the environment before a stage burns tokens on it.
- Open-run detection — a run already in flight is resumed, never overwritten.
- Profile — load
.clodex/profile.json, or interview once and write it. - Lane classification by blast radius: light (edit, fresh review, commit, no Codex), standard (one plan review, Codex implements, one whole-diff review) and full (the same at higher effort, with a confirm pass after a blocker). Audit keeps its own lane. The router picks and says so in one line; the user can override.
- Change boundary — record what was already dirty, and never let the run commit someone else's work.
Then it opens the run and hands to a stage skill.
This skill does not edit code, does not call Codex, and does not run release actions. The stage skills own all three.
Paths and commands
CLODEX_HOME="${CLODEX_HOME:-$HOME/.claude/skills/clodex}" # the dir holding this SKILL.md
STATE="$CLODEX_HOME/state/clodex_state.py"
REPO="$(git rev-parse --show-toplevel)"
cd "$REPO" # do this, do not just assume it
REMOTE="$(git rev-parse --abbrev-ref '@{upstream}' 2>/dev/null | cut -d/ -f1 || true)"
[ -n "$REMOTE" ] || REMOTE="$(git remote | head -1)" # empty = this repo has no remote
Shell variables do not survive between separate command invocations, so
re-establish this block at the top of any shell you run these procedures in.
Later sections use $REPO, $STATE, and $REMOTE as if it were already there.
Every command below runs from $REPO. git check-ignore, the repo
inspection in §3, and git add all resolve relative paths against the current
directory, so from a subdirectory they answer the wrong question — a correct
.gitignore reads as missing. If a step cannot cd, use git -C "$REPO" ….
| Thing | Path | Committed? |
|---|---|---|
| Run-state engine | $STATE |
catalogue |
| Profile schema | $CLODEX_HOME/profile.schema.json |
catalogue |
| Codex runner (stages only, never here) | $CLODEX_HOME/runner/run-codex.sh |
catalogue |
| Repo profile | $REPO/.clodex/profile.json |
yes |
| Run directory | $REPO/.clodex/<run-id>/ ($RUN_DIR below) |
no — gitignored |
What ships with it
28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- profile.schema.json 14 KB
- README.md 9.1 KB
- runner/envelope.schema.json 8.1 KB
- runner/run-codex.sh 31 KB runs code
- runner/test_runner.sh 50 KB runs code
- runner/validate_envelope.py 13 KB runs code
- state/bootstrap_check.py 11 KB runs code
- state/clodex_state.py 61 KB runs code
- state/cost.py 13 KB runs code
- state/counts.py 2.9 KB runs code
- state/fixtures/legacy-run.events.ndjson 24 KB
- state/fixtures/legacy-run.snapshot.json 26 KB
- state/fixtures/pilot-run.events.ndjson 26 KB
- state/inspect_repo.py 10 KB runs code
- state/lane_check.py 3.4 KB runs code
- state/plan_check.py 4.5 KB runs code
- state/prior_knowledge.py 9.2 KB runs code
- state/quota.py 18 KB runs code
- state/reducer.py 24 KB runs code
- state/release_reconcile.py 8.4 KB runs code
- state/schemas/event.schema.json 8.4 KB
- state/schemas/snapshot.schema.json 17 KB
- state/test_clodex_state.py 53 KB runs code
- templates/handoff.md 4.4 KB
- templates/lane-brief.md 5.7 KB
- templates/lane-report.md 2.8 KB
- templates/scenario-card.md 1.4 KB
- VERSION 6 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 14d ago Changed · +20 lines 4a0132e93657
- 1mo ago Changed · +5 lines d0b52634cc41
- 1mo ago Changed · +25 lines 253a6936f132
- 1mo ago First seen · 869 lines · 85 tokens per session scan A 2e78746794ae
clodex is a skill published in the GitHub repository jdpalumbo2/workbench (1 stars, last pushed 15d ago), licensed MIT. It adds 85 tokens to every session and 13,087 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
codex-autoresearch
Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomous optimization or managing an autoresearch run, not one-shot edits.
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
flue
Let agents control software, like Adobe Photoshop, Illustrator, After Effects, Premiere, Autodesk 3DS Max, Blender, Unity, Houdini, and Microsoft Office.
code-that-fits-in-your-head
Software-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-driven development. Use when writing or reviewing code, refactoring accidental complexity or a Big Ball of Mud, controlling technical or architectural debt in generated code, designing APIs and invariants…
rexai-image-generation
An image-generation skill that uses RexAI to create new images from text or transform existing images from other images. It returns the result as a local file.