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 instructions/minusblindfold/devloop/claude-mdgit clone --depth 1 https://github.com/minusblindfold/devloopWhat 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 | $0.00361 | $0.00361 |
| Opus 5 | $0.00180 | $0.00180 |
| Sonnet 5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
devloop CLAUDE.md 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 yesterday.
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.
What it actually says
devloop
Structured development workflow plugin for Claude Code.
Versioning
This project uses semver (MAJOR.MINOR.PATCH). When making changes that affect plugin behavior (skills, commands, hooks, rules), bump the version in both files before merging:
plugins/dl/.claude-plugin/plugin.json.claude-plugin/marketplace.json
Bump rules:
- Patch (1.1.x): bug fixes, typo corrections, doc-only changes
- Minor (1.x.0): new skills/commands, changed skill behavior, new rules
- Major (x.0.0): breaking changes to skill interfaces or plugin structure
Git
Always work on a feature branch off main. Never commit directly to main.
Testing skill changes
Editing plugins/dl/skills/ does not affect running sessions — the installed plugin cache lags this repo. Skill changes only take effect after reinstalling the plugin or running with claude --plugin-dir .; live-test them that way before release.
Doc sync
When changing skills or plugin config, update documentation to match.
Content mapping
plugins/dl/skills/*/SKILL.md→ Skills table inREADME.mddocs/rules.md→ Rules section inREADME.mdplugins/dl/.claude-plugin/plugin.json→ description inREADME.mdintro (README carries no version string)
Structural sync
- New skill → add to skills table in
README.md, update plugin.json keywords if relevant - Skill renamed or removed → update
README.mdskills table - Version bump → update in
plugin.jsonandmarketplace.json
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.
- yesterday First seen · 40 lines · 361 tokens per session scan A b0388a2b78bf
devloop CLAUDE.md is an instructions file published in the GitHub repository minusblindfold/devloop (1 stars, last pushed 1mo ago), licensed MIT. It adds 361 tokens to every session, about $0.0018 per session on Opus 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 instructions, from other repositories
ai-coding-primer CLAUDE.md
Instructions for ammonhaggerty/ai-coding-primer, covering claude.md, repository structure, guidebook chapters, constraints and writing tone.
claude-code-templates CLAUDE.md
Instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.
codexspec CLAUDE.md
Instructions for Zts0hg/codexspec, covering claude.md - codexspec development guide, project overview, purpose, technology stack and architecture.
trellis AGENTS.md
Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.
anchorlaw AGENTS.md
Instructions for unknowbug/anchorlaw, covering anchorlaw 项目 agents.md（项目级常驻指令）, 〇、开始工作前（每个 session 必做）, 一、项目定位（一句话）, 二、主工作流（judge 驱动流水线，v0.11） and 三、技能与宿主入口.
trellis copilot-instructions.md
Instructions for craigcossairt/trellis: Read and follow AGENTS.md at the repository root - it is the canonical instruction file for all AI agents on this project. Full methodology docs live in docs/methodology/: TDD workflow, bug-fix protocol, and session habits. Append bug patterns to docs/common-gotchas.md and…