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 skills/plamentsv/plamen/authorization-modelnpx skills add PlamenTSV/plamen --skill authorization-modelgit clone --depth 1 https://github.com/PlamenTSV/plamenWhat 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 | $0.00026 | $0.01668 |
| Opus 5 | $0.00013 | $0.00834 |
| Sonnet 5 | $0.00005 | $0.00334 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
authorization-model 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AUTHORIZATION_MODEL Skill (DAML)
Trigger Pattern: Always required for DAML audits Inject Into: Breadth agents, depth-state-trace, depth-external Finding prefix:
[DML-AM-N]Rules referenced: R4, R6, R12, R13
DAML's authorization model has no msg.sender. Authority flows through the transaction tree: the required authorizers of every node MUST be a subset of the parties who authorized the submission. A create requires the new contract's signatory parties; an exercise/fetch requires the choice's controller parties; an archive requires the signatories. Signatory authority propagates exactly ONE hop into a choice's consequences. The most common critical bug class is a choice whose controller is derived from a choice argument (privilege injection), or a choice that performs a privileged action with only one authorizer where joint authorization is required.
1. Choice-Authority Inventory
For EVERY choice in each template, record who must authorize it and what it does:
| Template.Choice | Consume-Mode | Controller Expr | Controller Source | Privileged Action? | Co-Auth Required? |
|---|---|---|---|---|---|
{T.C} |
consuming/nonconsuming/pre/postconsuming | {controller expr} |
FIXED-SIGNATORY / ARG-DERIVED / FETCHED | YES/NO | YES/NO |
Critical patterns to flag:
- A choice that moves value, changes ownership, or updates config but lists only ONE controller where the action affects multiple parties (single-where-joint →
[ELEVATE:MISSING_COAUTH]). - A
controllerexpression that reads a field of the choice argument rather than a template signatory/fixed party (privilege injection →[ELEVATE:PARAM_CONTROLLER], ALWAYS flag).
DAML note: controller p makes p the required authorizer AND an automatic observer. A controller derived from arg.someParty lets the caller name themselves as the authorizer — there is no msg.sender to constrain it.
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.
- 3d ago First seen · 102 lines · 26 tokens per session scan A 65dd37023f62
authorization-model is a skill published in the GitHub repository PlamenTSV/plamen (281 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,668 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 2026-08-30.
Other skills, from other repositories
prowler-compliance
Creates, syncs, audits and manages Prowler compliance frameworks end-to-end. Covers the two supported JSON schemas (universal multi-provider and legacy per-provider), the SDK model tree (legacy attribute classes, universal ComplianceFramework, ConfigRequirements guardrails), output formatters (legacy per-framework +…
law-18-07-auditor
A strict legal auditor for the Algerian Law 18-07 & Law 25-11 amendments on personal data protection, image publication rules (ANPDP Délibération 04/2026), and data sovereignty.
rgpd-auditor
A specialized compliance auditor. Scans architecture and code for strict adherence to the European GDPR (RGPD) regarding personal data protection.
advogado-criminal
Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
mod-actions
Comprehensive moderation toolkit: user actions (ban/mute/DM), strike system, image moderation, report handling, generation moderation, content/training moderation, and NCMEC/CSAM reporting. All via Civitai tRPC API.