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 agentmods add skills/jdpalumbo2/workbench/clodex-buildnpx skills add jdpalumbo2/workbench --skill clodex-buildgit 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-build)<a href="https://agentmods.dev/skills/jdpalumbo2/workbench/clodex-build"><img src="https://agentmods.dev/badge/skills/jdpalumbo2/workbench/clodex-build.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.14008 |
| Opus 5 | $0.00030 | $0.07004 |
| Sonnet 5 | $0.00012 | $0.02802 |
| Haiku 4.5 | $0.00006 | $0.01401 |
Grade D, and why
clodex-build scanned grade D with 3 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 today.
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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
never stage them, never revert them, never mention them in a contract except as Enumerates the file system for secretshighData exfiltration
Searching home directories for .env, .ssh, .aws or credential files is reconnaissance for credential theft.
for path in sorted(glob.glob(os.path.join(runner_state, "*", "*.envelope.json")) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
snap = json.loads(subprocess.check_output(["python3", sys.argv[1], "rebuild", sys.argv[2]])) How it starts
The opening of the file, as written. The whole thing — 1,064 lines — stays where its author put it; the contents beside it link to each section on GitHub.
clodex-build — small batches, an explicit contract, a reviewed delta
Overview
This stage turns an approved plan into commits. It owes the run one thing per batch, and all of it is fact in the event log rather than claim in a transcript:
| Fact | Event | In the manifest |
|---|---|---|
| what this batch may touch | batch:opened |
batches[].owned_paths |
| the delta was reviewed, and the verdict | batch:reviewed |
batches[].delta_review |
| the commit it landed in | batch:committed |
batches[].commit |
Plus, when an assumption breaks mid-flight, a plan amendment — never silent drift.
Where this stage ends. You prove each batch against its own test
expectations: the profile's test command green, plus your review of the delta.
You do not run the plan's declared evidence classes, record
verification:evidence, or decide anything about verification debt — that is
clodex-verify. You do not write the changelog, bump the version, tag, push, or
deploy — that is clodex-ship, and §2 makes those files forbidden to you.
You arrive here from clodex (which owns preflight, the profile, and the run
directory) or from clodex-plan (which owns the plan, its owned paths, and its
approval). If you were invoked without an absolute run directory, stop and
invoke clodex — do not go looking for a run yourself.
0. Paths and commands
CLODEX_HOME="${CLODEX_HOME:-$HOME/.claude/skills/clodex}" # the router's dir, not this one
STATE="$CLODEX_HOME/state/clodex_state.py"
RUNNER="$CLODEX_HOME/runner/run-codex.sh"
RUN_DIR="<the absolute run dir you were handed>"
SNAP="$(python3 "$STATE" rebuild "$RUN_DIR")"
REPO="$(printf '%s' "$SNAP" | python3 -c 'import json,sys;print(json.load(sys.stdin)["repo"])')"
PLAN="$(printf '%s' "$SNAP" | python3 -c 'import json,sys;print(json.load(sys.stdin)["plan"]["path"] or "")')"
cd "$REPO"
PROFILE="$REPO/.clodex/profile.json"
Shell variables do not survive between command invocations — re-establish this
block at the top of every shell you run these procedures in. Everything below
runs from $REPO; git add, git status, and the profile reads all resolve
relative paths against the current directory, so from a subdirectory they answer
the wrong question.
What ships with it
1 file 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.
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.
- today Changed · +5 lines a698f6d9fcf9
- 5d ago First seen · 1,059 lines · 60 tokens per session scan D 6333c3c88422
clodex-build is a skill published in the GitHub repository jdpalumbo2/workbench (1 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 14,008 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (subtle steering, enumerates the file system for secrets, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
git-commit
当用户明确要求"提交 Git 改动"、"生成 commit 信息"或"创建 git commit"时使用。仅用 Git 分析改动并自动生成 conventional commit 信息(可选 emoji);必要时建议拆分提交,默认运行本地 Git 钩子(可 --no-verify 跳过),提交后默认自动 push(可 --no-push 跳过)。.
commit
Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
git-workflow
Git 工作流专家。规范化版本控制,确保提交历史清晰可追溯。支持 Conventional Commits 规范、Pull Request 最佳实践、分支管理策略和自动化工作流。.
intuitive-squash
Squash local GSD or agent-generated commit history into a clean, reviewable story while preserving important fixes. Use when the user asks to squash commits, clean git history, compress phase commits, prepare a branch before PR, compare aggressive vs moderate squash options, or preserve hotfix/security commits during…
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI.