source-verifier

An agent that checks important code-graph claims against source files and tests without changing the repository.

In plain words
What is it for?
Use it to locate supporting files and tests, verify code-intelligence findings, and report concise evidence.
Why use it?
It separates behavior confirmed by code from suggestions made by a static graph and records remaining uncertainty.

Agent

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.

agentmods
npx agentmods add agents/r1ck29/claude-code-codegraph-harness/source-verifier
Clone the repo
git clone --depth 1 https://github.com/R1ck29/claude-code-codegraph-harness
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 109 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00020 $0.00109
Opus 5 $0.00010 $0.00055
Sonnet 5 $0.00004 $0.00022
Haiku 4.5 $0.00002 $0.00011

Measured yesterday against content hash 273d0c11ba15, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-verifier 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 yesterday.

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.

plugins/codegraph-evaluator/agents/source-verifier.md · 17 lines

What it actually says

You verify code-intelligence claims against source evidence.

  • Do not edit files or run mutation commands.
  • Locate the exact source and, where present, relevant tests.
  • Distinguish confirmed behavior from static-graph suggestions and unresolved runtime behavior.
  • Return concise file-and-line evidence and list any remaining uncertainty.
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. yesterday First seen · 17 lines · 20 tokens per session scan A 273d0c11ba15

Subscribe to this mod's changes

source-verifier is an agent published in the GitHub repository R1ck29/claude-code-codegraph-harness (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 20 tokens to every session and 109 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 2026-08-31.

Related

Other agents, from other repositories

mcp-tool-author

Adds a mode to one of basemind's 9 MCP domains end-to-end — mode enum variant, params, shim arm, helper body, CLI subcommand, smoke assertion, README row.

Goldziher/basemind · 45 tokens

sverklo-explore

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

sverklo/sverklo · 96 tokens

rust-perf-engineer

Reviews diffs touching the basemind scanner / extract / store / index paths for hot-path regressions — allocations, missed memmem opportunities, hashmap churn, parser pool misuse.

Goldziher/basemind · 42 tokens

cursor

Agent "cursor" from mareurs/codescout, covering cursor, one-time setup, register codescout as an mcp server, add workflow skills and add the code-reviewer agent.

mareurs/codescout · 0 tokens

harness-interpreter

Reads /tmp/basemind-harden-.log + per-repo metrics JSON, summarizes pass/fail with canary deltas, surfaces regressions. Cheap read-mostly subagent.

Goldziher/basemind · 44 tokens

lesson-learner

Use proactively when the user asks to encode insights or guidelines into CLAUDE.md. Triggers include phrases like "update your memory", "remember to do this", "learn from this", or "add this to the guidelines". Extracts generalizable principles from context and proposes targeted improvements to project documentation.

CRJFisher/ariadne · 66 tokens