check-claim

check-claim is a skill for Claude Code from ayeshakhalid192007-dev/graph-engineering-crash-course. It costs 55 tokens per session (1,086 once invoked), scanned A, original, MIT.

A checker for claims about whether a code change affects a particular module. It turns the claim into a graph fact and looks for that exact fact in the graph.

In plain words
What is it for?
Use it to verify claims such as “this change does not touch that module” and identify the graph edge supporting the result.
Why use it?
It gives a clear ACCEPT or REJECT result based on recorded graph data, without relying on the change's written description.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

Good fit Use it to verify claims such as “this change does not touch that module” and identify the graph edge supporting the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ayeshakhalid192007-dev/graph-engineering-crash-course/check-claim
Install

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.

Any agent
npx skills add ayeshakhalid192007-dev/graph-engineering-crash-course --skill check-claim
Clone the repo
git clone --depth 1 https://github.com/ayeshakhalid192007-dev/graph-engineering-crash-course

Made for: Claude Code.

Wrote 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.

agentmods badge for check-claim

README.md
[![agentmods](https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/check-claim/github.svg)](https://agentmods.dev/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/check-claim)
Your own site
<a href="https://agentmods.dev/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/check-claim"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/check-claim/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.

agentmods 80×15 button for check-claim

Your own site · 80×15
<a href="https://agentmods.dev/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/check-claim"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/check-claim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,086 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.01086
Opus 5 $0.00028 $0.00543
Sonnet 5 $0.00011 $0.00217
Haiku 4.5 $0.00006 $0.00109

Measured 9d ago against content hash 3693fb75ac1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

check-claim 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 9d 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.

starters/grounded-triple-checker/.claude/skills/check-claim/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

check-claim

This skill converts a claim shaped like "this change doesn't touch that module" into a (change, touches, module) triple and searches the graph's edge list for that exact subject/predicate/object combination. The change's own description is not part of the input at any step: reading it plays no role in whether the search finds a match, and no role in what verdict that match produces.

Instructions

You are a Claude Code skill implementing the grounded-triple-checker pattern. Follow these steps in order:

  1. Read the full graph first. Open sample-graph.example.json (or the file the user names) and parse its nodes and edges arrays before doing anything else.
  2. Resolve which claim(s) to check. If the user names a specific claim id, check only that one. Otherwise default to every claim-typed node in the graph — this kit's shipped scenario has two: claim-ch3002-no-license-touch and claim-ch3047-no-license-touch.
  3. Build the search triple. Pull the claim node's own about (the change id) and forbidden_module fields — do not parse these back out of the claim's free-text text field, and do not open the change node's description at this step. Assemble them into (about, "touches", forbidden_module); step 4 walks the graph's edges looking for that combination.
  4. Scan every edge in the graph, looking for one whose subject, predicate, and object all three line up with that triple. A touches edge from the right change to a different module doesn't count, and neither does an edge of a different predicate between the same two nodes.
  5. Decide the verdict from presence alone. A match found among the graph's edges means REJECT, with that exact edge cited as the reason; no match anywhere in the graph means ACCEPT. Do not consult the change's description field to double-check either outcome — a description that sounds convincing is not evidence, and neither is one that sounds suspicious.
  6. Handle the unverifiable case explicitly. If the claim's about change id or forbidden_module module id isn't found among the graph's nodes at all, report that claim as UNVERIFIABLE rather than defaulting it to ACCEPT. An edge that can't be looked up is not the same thing as an edge that's confirmed absent.
  7. Write the results to verdicts.json (or the path the user requested) in this kit's root: an array with one entry per claim, each holding claim_id, about, forbidden_module, decomposed_edge, edge_found, verdict, and citation (the exact matching edge for a REJECT, or null for ACCEPT/UNVERIFIABLE).
  8. Report a summary alongside the file: how many claims came back ACCEPT, REJECT, or UNVERIFIABLE, and the citation for every REJECT.

Read the full file on GitHub · 93 lines

Changes

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.

  1. 9d ago First seen · 93 lines · 55 tokens per session scan A 3693fb75ac1b

Subscribe to this mod's changes

check-claim is a skill published in the GitHub repository ayeshakhalid192007-dev/graph-engineering-crash-course (5 stars, last pushed 14d ago), licensed MIT. It adds 55 tokens to every session and 1,086 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

animate

Build a web animation: whether it should animate at all, the purpose, the tool, the properties, the easing curve, the duration, interruption and exit. Writes the CSS or Motion code for dropdowns, modals, toasts, tooltips, accordions, press feedback, stagger and scroll reveals. Use to animate something or make a…

ericrisco/rsc-harness · 75 tokens

building-agents

Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…

ericrisco/rsc-harness · 85 tokens

postgresdb

Use when PostgreSQL engine behaviour decides the answer — schema and type design, index choice, reading EXPLAIN on a slow query, zero-downtime DDL and backfills, or ops (roles, RLS, pooling, vacuum, partitioning, PITR). PG16, ORM-agnostic. NOT portable query logic (that is sql), NOT a managed provider's platform…

ericrisco/rsc-harness · 91 tokens

author-skill

Use when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into references/, writing its evals, auditing it against the rubric. NOT building a product feature (that is specify) and NOT designing an agent loop…

ericrisco/rsc-harness · 79 tokens

community

Use when building or running a persistent two-way community space — Discord, Telegram, Circle: platform choice, structure, onboarding, native→bot→human moderation, rituals, growth loops, health metrics. NOT churn of paying product customers (that is retention), NOT broadcast email (that is newsletter), NOT one live…

ericrisco/rsc-harness · 77 tokens

cpp

Use when writing, reviewing, modernizing, building, or debugging C++ - RAII and resource lifetime, smart-pointer ownership, move semantics and the Rule of Zero/Five, target-based CMake with FetchContent, and killing undefined behavior with ASan/UBSan/TSan plus clang-tidy. NOT borrow-checker / Result-Option / cargo…

ericrisco/rsc-harness · 81 tokens