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 skills add AnthonyAlcaraz/agentic-graph-rag-skills --skill constraint-guided-plan-validatorgit clone --depth 1 https://github.com/AnthonyAlcaraz/agentic-graph-rag-skillsWrote 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/anthonyalcaraz/agentic-graph-rag-skills/constraint-guided-plan-validator)<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/constraint-guided-plan-validator"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/constraint-guided-plan-validator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/constraint-guided-plan-validator"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/constraint-guided-plan-validator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00196 | $0.01817 |
| Opus 5 | $0.00098 | $0.00908 |
| Sonnet 5 | $0.00039 | $0.00363 |
| Haiku 4.5 | $0.00020 | $0.00182 |
Grade A, and why
constraint-guided-plan-validator 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 10d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constraint-Guided Plan Validator
Overview
In regulated environments a planning node must ensure plans respect domain constraints and business rules before committing to execution (Example 5-14): extract the constraints from the request, generate the plan, validate, and if validation fails, refine with the validator's feedback. The chapter pairs this with two further gates:
- Capability-model filter (DevOps hypothesis-formation node): the agent's operational boundaries are queryable data specifying which actions it may perform and at what privilege. "A hypothesis requiring direct database access gets filtered if the agent only has read-only monitoring permissions." This prevents proposing investigations it cannot execute.
- Ontological grounding: domain/range validation rejects operations that are syntactically valid but semantically nonsensical before they corrupt the decision.
This skill validates a plan against extracted constraints and a capability
model, returning a 0..1 conformance score plus structured per-step feedback.
Below threshold (0.8) the plan should be refined and re-validated.
Forbidden-action and capability violations are hard: any single one forces
passed=False no matter the score — a plan the agent cannot legally execute is
not "mostly fine."
In the DevOps latency investigation (account 123456789012), the agent holds
read-only monitoring permissions. A remediation plan whose step proposes
modify_db (write privilege) fails the capability gate and is sent back to the
planner; a plan that proposes only query_metrics and read_logs (read) with
the required record_incident step, within the 30-day emergency regulatory
deadline, passes.
When to Use
- Regulated / capability-bounded environments (insurance, healthcare, finance, privileged DevOps)
- A planning node must gate plans against business rules and operational authority before any action runs
- You want a refine-on-low-score loop driven by structured feedback
What ships with it
2 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.
- 10d ago First seen · 141 lines · 196 tokens per session scan A ccec3517cd0d
constraint-guided-plan-validator is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 196 tokens to every session and 1,817 once invoked, about $0.0010 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
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
jurisd-research
Expert Australian/NZ legal research and AGLC4 citation using the jurisd MCP server. Use when finding cases or legislation (AustLII), looking up a provision offline, formatting or resolving citations, building a pinpoint, tracing who-cites-what, or producing an AGLC4 bibliography. Triggers on case law, legislation…
repo_search
Search repository text through a deterministic first-class fak command.
container-manager-kg-ingestion
Snapshot a host's Docker/Podman/Swarm inventory into the epistemic-graph knowledge graph as typed OWL nodes via the container-manager-mcp MCP server — containers, images, volumes, networks, swarm services and nodes, with their :usesImage / :runsOn / :builtFrom links. Use when the agent must record live container state…
cortex-design
Use this skill to generate well-branded interfaces and assets for Cortex, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.