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/khaoss85/agent-crm/gemini-mdgit clone --depth 1 https://github.com/khaoss85/agent-crmWrote 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/khaoss85/agent-crm/gemini-md)<a href="https://agentmods.dev/instructions/khaoss85/agent-crm/gemini-md"><img src="https://agentmods.dev/badge/instructions/khaoss85/agent-crm/gemini-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 | $0.00347 | $0.00347 |
| Opus 5 | $0.00173 | $0.00173 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
agent-crm GEMINI.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 5d 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.
What it actually says
Gemini CLI guidance
Read AGENTS.md first and follow it as the canonical repository guidance. It is
the same guidance Claude Code and Codex receive; this file exists because Gemini
CLI loads GEMINI.md, not AGENTS.md.
Before substantial work, also read PRODUCT.md, ARCHITECTURE.md,
DECISIONS.md, and — for the current state of what is built versus designed —
docs/PROJECT_STATUS.md.
Non-negotiable rules:
- All CRM mutations go through module services or named workflows.
- Preserve validation, actor identity, audit and trace.
- Keep commercial policy deterministic; AI may recommend but cannot silently override approval rules.
- Code-generating or destructive MCP actions must remain explicit and safe by default.
- Use an ExecPlan for multi-file work and finish with
npm run verify.
The repository's task playbooks live in .claude/skills/ as SKILL.md files —
they are plain Markdown and apply to any agent. Read the one that matches the
task before starting: solve-business-goal for a stated business objective,
create-crm-module for a new object, create-crm-workflow for a lifecycle
step, the build-* skills for a named milestone, debug-crm-run for a failed
run, and adversarial-review before a merge.
The MCP server for a project is configured in .mcp.json; Gemini CLI reads MCP
servers from its own settings, so point it at
node --no-warnings packages/mcp/bin/server.js with CRM_DB_PATH set to the
project's SQLite file.
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.
- 5d ago First seen · 30 lines · 347 tokens per session scan A d1600630745d
agent-crm GEMINI.md is an instructions file published in the GitHub repository khaoss85/agent-crm (2 stars, last pushed 2d ago), licensed MIT. It adds 347 tokens to every session, about $0.0017 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-workbench-mcp AGENTS.md
AGENTS.md instructions for hrishikesh-thakre/ai-workbench-mcp, covering agents.md, repository summary, read first, working rules and current direction.
matt-skills-with-to-goal CLAUDE.md
Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
pixir CLAUDE.md
Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.
Agent-Memory-Bridge AGENTS.md
Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.