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.
git 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/commands/kitokoh/leopardo-hr/speckit.specify)<a href="https://agentmods.dev/commands/kitokoh/leopardo-hr/speckit.specify"><img src="https://agentmods.dev/badge/commands/kitokoh/leopardo-hr/speckit.specify.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 | $0.00014 | $0.00362 |
| Opus 5 | $0.00007 | $0.00181 |
| Sonnet 5 | $0.00003 | $0.00072 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
speckit.specify 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 8d 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
User Input
$ARGUMENTS
{CORE_TEMPLATE}
🔴 Leopardo Payroll Compliance Gate (auto-injected by preset leopardo-payroll)
After generating the spec above, verify and append the following section before saving:
Does this spec touch api/app/Modules/Payroll/?
If YES — append to the spec:
## Conformité Paie (obligatoire)
- **Pays ciblé** : [CODE ISO]
- **Référence** : docs/payroll/{PAYS}_COMPLIANCE.md
- **Référence légale** : [CGI art. XX / Code du travail art. YY]
### Golden tests requis (calculés à la main)
1. SMIG → net exact avec calcul commenté
2. Cadre moyen → IRG/IRPP + cotisations + net
3. Plafond cotisation → cotisation sur cap, pas sur brut
### Tenant isolation requis
- Tout endpoint : test `assert 404 cross-tenant`
- Toutes les requêtes Eloquent : `->where('company_id', ...)`
### CI
- PHPStan strict `[OK] No errors`
- Coverage Payroll ≥ 80 %
- CHANGELOG.md mis à jour
If NO — no additional section needed.
Anti-duplicate check
Before finalizing this spec, run:
gh issue list --state open --label "payroll" --json number,title,assignees | head -20
If a similar spec/issue already exists and is assigned → stop and contribute to that issue instead.
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.
- 8d ago First seen · 55 lines · 14 tokens per session scan A d47a61f41386
speckit.specify is a command published in the GitHub repository kitokoh/leopardo-hr (10 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 362 once invoked, about $0.0001 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 commands, from other repositories
sap-session-add-evidence
A command for adding a new evidence bundle to an existing SAP Evidence Loop investigation. An evidence bundle is a checked collection of files and related details used to support an investigation.
sap-year-end
A guided SAP process for closing the financial year, including balance carry-forward, asset closing, tax provisions, consolidated financial statements, Korean IFRS disclosures, and audit preparation.
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
plan-feature
Plan a feature from BRD-lite brief or clear intent into PRD (What), decisions, implementation plan, and task slices.
retro-learn
Convert delivery findings into skill, eval, workflow, and documentation improvements.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.