What is monomind-dev-rules?

A set of operating rules for an automated coding agent working in a software repository. It defines where work happens, how temporary files and Git branches are handled, and how tests and evidence are recorded.

Use it to guide repository work, create isolated worktrees, run commands with the required environment, preserve evidence, and report independent test results.

It reduces accidental changes to the main checkout and keeps separate tasks, command settings, and test results organised. It also gives the agent repeatable rules instead of relying on remembered details.

monomind-dev-rules — Skill for Claude Code and Codex by monoes

Install

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.

Any agent

npx skills add monoes/monomind --skill monomind-dev-rules

Clone the repo

git clone --depth 1 https://github.com/monoes/monomind

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/monoes/monomind/monomind-dev-rules/github.svg)](https://agentmods.dev/skills/monoes/monomind/monomind-dev-rules)

Your own site

<a href="https://agentmods.dev/skills/monoes/monomind/monomind-dev-rules"><img src="https://agentmods.dev/badge/skills/monoes/monomind/monomind-dev-rules/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/monoes/monomind/monomind-dev-rules"><img src="https://agentmods.dev/badge/skills/monoes/monomind/monomind-dev-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,717 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00066	$0.02717
Opus 5.5	$0.00026	$0.01087
Sonnet 5.5	$0.00013	$0.00543
Haiku 4.5	$0.00007	$0.00272

Measured yesterday against content hash f0f83e69ffa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

monomind-dev-rules 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.

.monomind/org-skills/monomind-dev-rules/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

monomind-dev rules (every role, every command)

Names used below. REPO is the main checkout — the directory your session starts in (pwd before you cd anywhere); it is on branch main. RUN is REPO/.monomind/orgs/monomind-dev/runs/<run-id> and holds ledger.json, plans/, logs/, evidence/ and REPORT.md. Each item works in its own worktree WT=REPO/.monomind/orgs/monomind-dev/work/<item-id> on branch dev/<item-id>. TMPDIR is $HOME/mdev-tmp. Every task message gives you the run id, the item id, the SHA to work on and the paths of earlier evidence — use those, never values remembered from an earlier task or run.

The main checkout

REPO may hold the owner's own uncommitted work: never modify, stash, reset, checkout or commit it. Only integrator changes local main, and only by fast-forward.

Environment

Prefix EVERY command that runs node, pnpm, npm, vitest or monomind with env -u MONOMIND_SDK_AGENT -u MONOMIND_HOOK_QUIET -u MONOMIND_GRAPH_GATE -u MONOMIND_NO_LOCAL_EMBEDDINGS MONOMIND_CRASH_REPORTING=off MONOMIND_AUTO_UPDATE=false CI=true TMPDIR=$HOME/mdev-tmp. Org sessions inject variables that silently change monomind's own behavior (issue #249).
Never write under /tmp: it is a RAM tmpfs with a per-user quota, and filling it breaks every shell.
SCRATCH: files you need to Read/Write/Edit with the file tools go in REPO/.monomind/orgs/monomind-dev/scratch/<item-id>-<check> (the file tools cannot reach paths outside the repo, issue #303). Sample projects that monograph must watch, and fake HOMEs, go in $HOME/mdev-tmp/<item-id>-<check> and are handled with Bash only (no dot-directories there: monograph's watcher ignores dot-segment paths).

Git

Never run git config in any checkout of this repo (worktrees share .git/config; issue #250).
NEVER use git stash in any form: the stash stack is shared by every worktree and the owner has entries on it (issue #300). Use git diff > $SCRATCH/x.patch
- git apply -R, or a scratch worktree at the base SHA.
Known policy gaps (#299): at policy.git read, merge-base, ls-remote, show-ref, reflog are denied — use git diff main...HEAD / git log main..HEAD instead.
Commit only with GIT_AUTHOR_NAME=nokhodian [email protected] GIT_COMMITTER_NAME=nokhodian [email protected] git commit using conventional commits (when it resolves an issue, put Fixes #N in the body; a bare (#N) leaves the issue open), and NO trailers (no Co-Authored-By, Claude-Session or 'Generated with').
Stage explicit paths, never git add -A / git add ..
Never push, never touch origin, npm or GitHub.

Read the full file on GitHub · 164 lines

Changes

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 · 164 lines · 66 tokens per session scan A f0f83e69ffa7

Subscribe to this mod's changes

monomind-dev-rules is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 2,717 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 2026-11-05.

Building agents Git and workflow agent-harness agentic-framework agentic-os engineering operations orchestration-systems

monomind-dev-rules next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
monomind-dev-rulesmonoes/monomind	Skill	23	today	Apache-2.0	A	66	Claude Code, Codex
publish-harnessruvnet/metaharness	Skill	738	yesterday	MIT	A	37	Claude Code
agentic-jujutsuruvnet/ruflo	Skill	81k	yesterday	MIT	A	26	Claude Code
github-automationruvnet/ruflo	Skill	81k	yesterday	MIT	A	61	Claude Code
ce-worktreeEveryInc/compound-engineering-plugin	Skill	26k	yesterday	MIT	A	46	Claude Code
ce-resolve-pr-feedbackEveryInc/compound-engineering-plugin	Skill	26k	yesterday	MIT	A	60	Claude Code
diag-harnessruvnet/metaharness	Skill	738	yesterday	MIT	A	85	Claude Code