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/locking-semanticsnpx skills add PlamenTSV/plamen --skill locking-semanticsgit 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 | $0.00038 | $0.01427 |
| Opus 5 | $0.00019 | $0.00714 |
| Sonnet 5 | $0.00008 | $0.00285 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
locking-semantics 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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LOCKING_SEMANTICS Skill (DAML)
Trigger Pattern: Always required for DAML audits — self-skip if no lock pattern present Inject Into: Breadth agents, depth-state-trace, depth-edge-case Finding prefix:
[DML-LK-N]Rules referenced: R8, R10, R14
DAML has no native lock primitive; locking is emulated by a template field (locked : Bool, lockedUntil : Time, a held lock contract, or a separate Locked template wrapping the asset). The invariant is: while locked, the asset MUST NOT be split, merged, transferred, or archived through any path; and the value MUST be conserved across the lock→unlock cycle. The two high-yield bugs are lock-bypass (a choice that moves the asset ignores the lock field) and lock-erase (a choice recreates the asset successor dropping the locked field). If no template carries a lock field / lock wrapper, this skill self-skips.
1. Lock-State Inventory
Identify every lock mechanism and the asset it protects:
| Template | Lock Mechanism | Lock Field/Wrapper | Set By (choice) | Cleared By (choice) | Asset Protected |
|---|---|---|---|---|---|
{T} |
bool field / time field / Locked wrapper | {locked / lockedUntil} |
{choice} |
{choice} |
{asset field} |
DAML note: A lock encoded as a plain Bool/Time field on the asset template is only honored if EVERY value-moving choice reads it. A lock encoded as a separate wrapper template is only honored if the underlying asset cannot be exercised directly while wrapped.
2. Lock-Honoring Audit (lock-bypass)
For EVERY value-moving choice on a lockable template, verify it checks the lock:
| Template.Choice | Moves/Splits/Merges/Archives Asset? | Reads Lock Field? | Lock Check Expr | Bypassable? |
|---|---|---|---|---|
{T.C} |
YES/NO | YES/NO | assertMsg "locked" (not locked) / NONE |
[DML-LK-N] if moves while locked |
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.
- 2d ago First seen · 86 lines · 38 tokens per session scan A 2fc882ed5f15
locking-semantics is a skill published in the GitHub repository PlamenTSV/plamen (281 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,427 once invoked, about $0.0002 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-ui
Prowler UI-specific patterns. For generic patterns, see: typescript, react-19, nextjs-16, tailwind-4. Trigger: When working inside ui/ on Prowler-specific conventions (shadcn, folder placement, actions/adapters, shared types/hooks/lib).
prowler-test-api
Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).
prowler-pr
Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label), or when inspecting PR-related GitHub workflows like conventional-commit.yml…
tailwind-4
Tailwind CSS 4 patterns and best practices. Trigger: When styling with Tailwind (className, variants, cn()), especially when dynamic styling or CSS variables are involved (no var() in className).
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
react-19
React 19 patterns with React Compiler. Trigger: When writing React 19 components/hooks in .tsx (React Compiler rules, hook patterns, refs as props). If using Next.js App Router/Server Actions, also use nextjs-16.