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/kitokoh/leopardo-hr/agents-mdgit clone --depth 1 https://github.com/kitokoh/leopardo-hrWrote 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/kitokoh/leopardo-hr/agents-md)<a href="https://agentmods.dev/instructions/kitokoh/leopardo-hr/agents-md"><img src="https://agentmods.dev/badge/instructions/kitokoh/leopardo-hr/agents-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 | $0.08633 | $0.08633 |
| Opus 5 | $0.04317 | $0.04317 |
| Sonnet 5 | $0.01727 | $0.01727 |
| Haiku 4.5 | $0.00863 | $0.00863 |
Grade A, and why
leopardo-hr AGENTS.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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Guide de travail Leopardo RH
Derniere mise a jour : 2026-08-26
Ce fichier doit etre lu au debut de chaque nouvelle session agent. Il doit aussi etre mis a jour a chaque push ou merge vers main, comme le CHANGELOG.md, des qu'une lecon operationnelle peut eviter de perdre du temps plus tard.
NOUVEL AGENT ? Commence par lire
dev-hub/prompts/00_AGENT_QUICK_CARD.md(2 min) pour une carte de reference rapide. Ce fichier AGENTS.md est le guide complet.
⚡ Spec-Driven Development — Spec Kit (NOUVEAU 2026-08-14)
Leopardo HR utilise desormais GitHub Spec Kit pour structurer tout travail significatif.
Lire .specify/constitution.md — c'est la loi fondamentale du projet.
Commandes disponibles (GitHub Copilot skills)
| Commande | Role |
|---|---|
/speckit-constitution |
Principes directeurs du projet |
/speckit-specify |
Creer une spec avant de coder |
/speckit-clarify |
Clarifier les ambiguites (avant plan) |
/speckit-plan |
Plan technique et architecture |
/speckit-tasks |
Generer les taches actionnables |
/speckit-analyze |
Verifier coherence avant implementation |
/speckit-implement |
Executer les taches |
/speckit-converge |
Detecter le travail restant |
Presets actifs (injectes automatiquement dans toute spec)
| Preset | Se declenche sur |
|---|---|
leopardo-payroll |
Toute spec touchant api/app/Modules/Payroll/ |
leopardo-multitenancy |
Toute spec ajoutant une table ou un endpoint API |
leopardo-dz |
Specs paie algeriennes (IRG/CNAS) |
leopardo-cemac |
Specs paie zone CEMAC (CM/GA/CG/XAF) |
leopardo-cedeao |
Specs paie zone CEDEAO (CI/SN/BF/ML/XOF) |
Workflow standard (remplace la creation manuelle d'issues)
1. /speckit-specify "description de ce que tu veux construire"
2. /speckit-clarify (si ambiguite)
3. /speckit-plan (architecture)
4. /speckit-analyze (verifier dependances manquantes)
5. /speckit-tasks (generer les taches)
6. /speckit-implement (coder)
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.
- today Changed · -634 lines · -32,286 tokens per session 7247ca67df50
- 5d ago First seen · 1,047 lines · 40,919 tokens per session scan A 38989119a4b5
leopardo-hr AGENTS.md is an instructions file published in the GitHub repository kitokoh/leopardo-hr (10 stars, last pushed today), licensed MIT. It adds 8,633 tokens to every session, about $0.0432 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
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
laravel AGENTS.md
AGENTS.md instructions for laravel/laravel, covering laravel application, prerequisites and agent setup.
mcp-erpnext AGENTS.md
AGENTS.md instructions for Casys-AI/mcp-erpnext, covering agents.md, project overview, project structure & module organization, build, test, and development commands and run all tests (also: deno task test).
LarAgent AGENTS.md
Instructions for MaestroError/LarAgent, covering purpose, key principles, planning, executing plan and testing.
wind docs.instructions.md
Instructions for fluttersdk/wind, covering documentation conventions (doc/), file shape (every doc file), wfoo, basic usage and props.
mcp-erpnext CLAUDE.md
Claude Code instructions for Casys-AI/mcp-erpnext: See AGENTS.md for all repository guidelines, architecture, conventions, and task recipes.