Borrowing it
Nothing to install: this file belongs to docxology/codomyrmex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/docxology/codomyrmex/main/.agent/skills/desloppify/SKILL.mdgit clone --depth 1 https://github.com/docxology/codomyrmexWrote 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/docxology/codomyrmex/desloppify)<a href="https://agentmods.dev/skills/docxology/codomyrmex/desloppify"><img src="https://agentmods.dev/badge/skills/docxology/codomyrmex/desloppify/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/docxology/codomyrmex/desloppify"><img src="https://agentmods.dev/badge/skills/docxology/codomyrmex/desloppify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.00996 |
| Opus 5.5 | $0.00027 | $0.00398 |
| Sonnet 5.5 | $0.00014 | $0.00199 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
desloppify 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 1mo 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Desloppify
Goal: raise the strict score. The scoring resists gaming; improvements require real code quality work.
1. Install (Python 3.11+)
Upstream install:
pip install --upgrade "desloppify[full]"
Codomyrmex: prefer uv — after uv sync, in the project environment:
uv pip install "desloppify[full]"
For a global CLI, use uv tool install with the same extra if you want desloppify available outside the project venv.
2. Workflow guide for your IDE
Install the bundled workflow instructions for the user’s stack:
desloppify update-skill claude # or: cursor, codex, copilot, droid, windsurf, gemini
Default to cursor when the session is Cursor; otherwise match the user’s stated tool.
3. Local state and git
Keep .desloppify/ out of version control (local scan state). This repo already ignores .desloppify/ in .gitignore; do not commit that directory.
4. Excludes before scan
Before the first meaningful scan, identify paths that should not be analyzed (vendor trees, build output, generated code, git worktrees, huge submodules, caches).
- Run
desloppify exclude <path>for obvious noise. - Pause and ask the human before excluding anything ambiguous.
Codomyrmex-oriented examples (exclude when appropriate, not blindly): node_modules/, htmlcov/, .gitnexus/, __pycache__/, .venv/, venv/, submodule checkouts, src/codomyrmex/agents/hermes/evolution/ (special dependency layout per CLAUDE.md), vendored or generated trees already listed in .gitignore.
5. Scan
desloppify scan --path .
Use . for the whole repo, or a subtree (e.g. src/). Rescan periodically after batch fixes.
6. Main loop — next is the queue
desloppify next is the living execution queue, not the full backlog. It names what to fix now, which file, and the resolve command to run when done.
Repeat until clear:
- Run
desloppify next. - Implement the fix properly (large refactors and small fixes deserve the same care).
- Run the exact resolve command from the output.
- Go to step 1.
What ships with it
2 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.
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.
- 1mo ago First seen · 104 lines · 68 tokens per session scan A 381184c07f38
desloppify is a skill published in the GitHub repository docxology/codomyrmex (11 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 996 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 2026-08-30.
Other skills, from other repositories
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
resolve-drive-pr
Drive an open PR through Polly/OCR, validation, and maintainer handoff.
resolve-review-pr
Review an existing fix PR using the audited repro and full diff, preserving branch and approval rules.
otto-impact-assessment
Check the final diff's consumers, focused tests, evidence, and gaps.
feature-publish
Commit the feature, write the PR body, publish in the selected mode, and drive the PR.
describe-pr
Only use when the user explicitly invokes this skill by name.