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/rjmurillo/ai-agents/universalgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/instructions/rjmurillo/ai-agents/universal)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/universal"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/universal.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 | $0.02189 | $0.02189 |
| Opus 5 | $0.01094 | $0.01094 |
| Sonnet 5 | $0.00438 | $0.00438 |
| Haiku 4.5 | $0.00219 | $0.00219 |
Grade C, and why
ai-agents universal.instructions.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
prohibition on `rm -rf` that does not exist, and How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal Rules
These rules apply to every change in this repository.
MUST
- Branch discipline. MUST NOT push or commit directly to
mainormaster. Create a feature branch first. - Issue linkage. Every PR MUST reference an issue with
Fixes #<n>orRefs #<n>in the description. - Verify closing keywords against the diff before merging.
Fixes #<n>closes on merge; tie each claim to a named hunk. Downgrade unsupported claims toRefs #<n>with reason. Missing closing keywords are not automatically defects. Agent-authored PR bodies SHOULD useThese references do not close their linked items:for bareRefs. Read the body before adding a closing keyword to another author's PR. Post-merge body edits are inert; close orphaned issues with a comment citing the merge commit. Evidence: on 2026-08-03, 15 claimed closing keywords across five PRs were unsupported, and four of seven keyword-free PRs repaired from title matches explicitly should not close the issue. - Verify a red remote check with equivalent evidence, or report it unreproduced. MUST NOT claim a red remote check is cleared by a local run unless the checker, ruleset, flags, and version are demonstrably identical. State the command and why it is the same check; if you cannot, say the check is red and you could not reproduce it. A different tool produces evidence about a different check, and calling that "resolved" tells the reader to disregard a live finding.
- Conventional commits. Commit messages MUST follow
<type>(<scope>): <desc>and include aCo-Authored-By:trailer when authored with an AI agent. - Atomic commits. Each commit MUST touch five or fewer authored files (see
AGENTS.mdboundaries). Hook-generated companions (session episodes, MCP config, agent catalog, memory index) are exempt and do not count toward the limit. - No secrets. MUST NOT commit credentials, tokens, or API keys. Secrets live in environment variables or the secrets manager.
- Pin Actions to SHA. New GitHub Actions references MUST pin to a commit SHA, never a floating tag.
- Session continuity. Long-running issue work MUST preserve continuity in the per-issue handoff and Serena memory. Session log creation is discontinued; a log that is already staged still validates.
- Git identity cannot prove a human acted.
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 · 119 lines · 2,189 tokens per session scan C 6990cf6c1bfa
ai-agents universal.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It adds 2,189 tokens to every session, about $0.0109 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
5dive CLAUDE.md
Claude Code instructions for 5dive-ai/5dive, covering 5dive cli — contributor rules and hard rule: no real pii in public artifacts (dive-1774).
claude-capsule-kit CLAUDE.md
Instructions for arpitnath/claude-capsule-kit, covering capsule kit v4.0, rules, context system (capsule), wikilink layer and docs.
sciclaw AGENTS.md
AGENTS.md instructions for drpedapati/sciclaw: For end-to-end implementation and pull-request work, use the vendored repository skill at .agents/skills/ship-job/SKILL.md. Read it completely before changing files, and use .agents/skills/ship-job/references/sciclaw-release.md for any separately authorized merge…
carmenta AGENTS.md
AGENTS.md instructions for carmentacollective/carmenta, covering project context for ai assistants, anti-patterns to avoid, always apply rules, project overview and directory documentation.
carmenta CLAUDE.md
Claude Code instructions for carmentacollective/carmenta, a project described as: A heart-centered AI for creating at the speed of thought.
Alex_Plug_In release-process.instructions.md
Version control, changelog generation, and publish workflows for software releases.