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/liuyingxuvka/flowguard/flowguard-behavior-commitment-ledgernpx skills add liuyingxuvka/FlowGuard --skill flowguard-behavior-commitment-ledgergit clone --depth 1 https://github.com/liuyingxuvka/FlowGuardWrote 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/skills/liuyingxuvka/flowguard/flowguard-behavior-commitment-ledger)<a href="https://agentmods.dev/skills/liuyingxuvka/flowguard/flowguard-behavior-commitment-ledger"><img src="https://agentmods.dev/badge/skills/liuyingxuvka/flowguard/flowguard-behavior-commitment-ledger.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 | $0.00037 | $0.00678 |
| Opus 5 | $0.00018 | $0.00339 |
| Sonnet 5 | $0.00007 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
flowguard-behavior-commitment-ledger 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FlowGuard Behavior Commitment Ledger
Purpose
Maintain one BehaviorCommitmentLedger: every external promise has source evidence, one disposition, one owner, and current Primary Path Authority.
Entrypoint Scope
This standalone FlowGuard satellite skill owns behavior_commitment_ledger (public_owner) and its PPA handoff.
Local Material Routing
After admission, read references/behavior_commitment_ledger_protocol.md for all fields, modes, lookup, and projections.
Entrypoint Acceptance Map
Accept a bounded source inventory and mode; register ownership; block coverage, relation, freshness, or PPA gaps.
Use When
- Use for the six ledger modes: bootstrap, add, change, remove/replace, gap backfill, or miss check.
Do Not Use When
- Do not inventory internals or replace sibling evidence owners; return ordinary modeling to
flowguard.
Required Workflow
- Freeze boundary, mode, exact source ids, and bounded repository root; resolve each direct, anchored, semicolon-composite, or bounded-glob source through the canonical live source-identity audit before trusting its stored inventory revision/fingerprint.
- Give every source one
modeled|delegated|scopeddisposition with evidence or reason; modeled behavior gets one plane, actor kind, stable commitment, owner, typed relations, lookup, and lifecycle. - Bind one current-green
primary_path_id; runreview_behavior_commitment_ledger(..., project_root=...)so current source content, membership, inventory revision, and discovery evidence are live-checked, then hand DCAR/TestMesh/risk evidence downstream. - For an explicit blueprint claim, hand off only external commitment/source/path ids, owner references, and the ledger fingerprint. Internal files, symbols, helpers, implementation dispositions, and developer activity never enter BCL.
Hard Gates
- Model-purpose gate: freeze task-specific failure(s); bind native good/bad-per-failure/oracle/current evidence. Reusable types are not fixed-purpose: no mode/fallback; only FlowGuard-declared checks may support completion claims. Require the real FlowGuard check engine and AGENTS.md managed record; forbid a fake mini-framework.
- Missing, unsafe, unbounded-glob, empty-glob, missing-anchor, duplicate-member, changed-content, changed-membership, or stale top-inventory sources block broad confidence even when stored rows say
current; duplicate sources, conflicting dispositions, owner overlap, stale PPA, untyped relations, or ambiguous authority also block. - Broad discovery is only for bootstrap/gap backfill; ordinary changes stay affected-only.
- BCL owns visible promises, not target roles, permissions, activity logs, internal code, resources, or implementation completeness. A blueprint may reference both independent owners by fingerprint.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 40 lines · 37 tokens per session scan A 2d7a99776c21
flowguard-behavior-commitment-ledger is a skill published in the GitHub repository liuyingxuvka/FlowGuard (2 stars, last pushed 10d ago), licensed MIT. It adds 37 tokens to every session and 678 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 2026-08-31.
Other skills, from other repositories
backend-idempotency
Use this skill when the user says 'idempotency', 'idempotent', 'idempotency key', 'exactly-once', 'retry safety', 'deduplication', 'duplicate detection', 'idempotent endpoint', 'safe retry'. This skill implements idempotency keys and exactly-once semantics so retries never result in duplicate side effects. Applies to…
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
review-agents-md
Audit Dograh AGENTS.md files for drift against the live repo and for bad scope boundaries between parent and child docs. Use when the user asks to review existing AGENTS files, identify stale guidance, decide whether a subtree needs its own AGENTS.md, or update the AGENTS.md hierarchy under the repo root, api/, or ui/.
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.