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/opensesh/karimo/claude-mdgit clone --depth 1 https://github.com/opensesh/KARIMOWrote 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/opensesh/karimo/claude-md)<a href="https://agentmods.dev/instructions/opensesh/karimo/claude-md"><img src="https://agentmods.dev/badge/instructions/opensesh/karimo/claude-md.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 | $0.02987 | $0.02987 |
| Opus 5 | $0.01494 | $0.01494 |
| Sonnet 5 | $0.00597 | $0.00597 |
| Haiku 4.5 | $0.00299 | $0.00299 |
Grade A, and why
KARIMO CLAUDE.md scanned grade A 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl -s "https://api.github.com/repos/opensesh/KARIMO/releases/latest" | grep tag_name How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KARIMO Source Repository Rules
Release Protocol (MANDATORY)
When changes impact target repositories (installed KARIMO projects), you MUST complete ALL steps below. The release is NOT complete until the GitHub Release exists AND is verified via API.
Preferred Method: Release Script
Use the release script for atomic, verified releases:
.karimo/scripts/release.sh 8.3.0 # Full release
.karimo/scripts/release.sh 8.3.0 --dry-run # Preview only
The script handles: version bump, commit, tag, push, release creation, and API verification.
Manual Release Checklist (if not using script)
[ ] 1. VERSION BUMP
- Update `.karimo/VERSION` with new semver
- Update `version` field in `.karimo/MANIFEST.json` to match
[ ] 2. CHANGELOG ENTRY
- Add entry to `CHANGELOG.md` under new version header
- Format: `## [X.Y.Z] - YYYY-MM-DD`
- Include: Added, Changed, Fixed, Removed subsections as needed
[ ] 3. DOCUMENTATION UPDATES
- README.md — Update version badge
- .karimo/docs/ARCHITECTURE.md — Update version header
- .karimo/docs/COMMANDS.md — If slash commands changed
- .karimo/docs/GETTING-STARTED.md — If setup flow changed
[ ] 4. COMMIT ALL CHANGES (BEFORE TAGGING)
- Commit version bump, changelog, AND documentation
- Push to origin/main
- CRITICAL: All changes must be committed BEFORE creating tag/release
[ ] 5. CREATE TAG AND RELEASE (ATOMIC)
- git tag vX.Y.Z
- git push origin vX.Y.Z
- gh release create vX.Y.Z --title "vX.Y.Z" --notes "..."
- Do these in immediate sequence
[ ] 6. VERIFY VIA API (REQUIRED)
- curl -s "https://api.github.com/repos/opensesh/KARIMO/releases/latest" | grep tag_name
- Must show your new version
- If not, the release is BROKEN
CRITICAL: Never Move Tags After Release
DO NOT run these commands after creating a release:
# DANGEROUS - orphans the release:
git tag -d vX.Y.Z && git tag vX.Y.Z # Moving tag
git tag -f vX.Y.Z # Force-updating tag
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.
- 6d ago First seen · 322 lines · 2,987 tokens per session scan A b73e381675b0
KARIMO CLAUDE.md is an instructions file published in the GitHub repository opensesh/KARIMO (284 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 2,987 tokens to every session, about $0.0149 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
ConsultMe CLAUDE.md
Claude Code instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
testivai-oss CLAUDE.md
Claude Code instructions for testivai/testivai-oss, covering testivai-oss — claude code guide, repo layout, package manager, common commands and architecture — how the oss lane works.
ai-usagebar CLAUDE.md
Claude Code instructions for akitaonrails/ai-usagebar, covering claude.md, release checklist — must do all of these, hard invariants — never break these, secret-discipline rules (learned the hard way) and live api smoke discipline.