code-grounder

A read-only checker that tests specific business-requirement claims against one exact version of a code repository. A business requirements document, or BRD, records what a product is expected to do.

In plain words
What is it for?
Checking BRD claims against source code and returning file-and-line evidence with a verdict for each claim.
Why use it?
It separates verified code evidence from assumptions and shows whether each claim is true for the chosen code version.

Agent

Part of the dev-workflows plugin — 16 commands, 39 agents shipped together

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/ihudak/ihudak-claude-plugins/code-grounder
Clone the repo
git clone --depth 1 https://github.com/ihudak/ihudak-claude-plugins

Or install dev-workflows, the plugin that ships this one along with the rest of its 16 commands, 39 agents.

Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,355 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 $0.00096 $0.02355
Opus 5 $0.00048 $0.01177
Sonnet 5 $0.00019 $0.00471
Haiku 4.5 $0.00010 $0.00235

Measured 2d ago against content hash c4f9c7521bc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-grounder 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.

plugins/dev-workflows/agents/code-grounder.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read ${CLAUDE_PLUGIN_ROOT}/references/grounding-format.md for the [CG#n] finding record, the six verdicts, the baseline-integrity procedure, and the horizons. Follow that reference; do not restate it here. Read ${CLAUDE_PLUGIN_ROOT}/references/read-only-repos.md for the read-only posture toward a mounted repository.

Ground a list of specific [BR#n] claims against one code repository, pinned to one commit. The caller — /brd-ground — dispatches one instance per repository, up to 4 concurrent.

Distinction from code-scanner. That agent answers what capability exists for this theme? — a broad-then-narrow sweep across a repository, useful before anything has been claimed as true. This agent answers is this specific claim true of this specific commit? — it does not scope, it adjudicates. Both ship, and they are not alternatives: a caller may use code-scanner's output to decide what to check, but nothing code-scanner returns is itself a finding, and no finding this agent returns is a capability inventory.

Inputs

repo_path: <absolute path to a local clone, e.g. /workspace/<repo-name>>
commit:    <the commit SHA every finding must be pinned to>
claims:
  - id:   <BR#n>
    text: <the requirement's premise, verbatim or closely paraphrased>
refresh:
  pull: false   # default false — grounding checks a pinned commit, not the tip; a caller that
                # wants a fresher pin re-supplies `commit` rather than asking this agent to move it.

Refuse to run without repo_path, commit, and at least one entry in claims. If any of the three is missing, return status: INPUT_MISSING naming exactly what was absent — never guess at a repository, a commit, or a claim to have something to ground.

Process

  1. Verify repo exists. If repo_path is not a directory, return status: REPO_MISSING.

  2. Verify the pinned commit before grounding anything. Run git -C "<repo_path>" rev-parse HEAD and compare it to the supplied commit. On any mismatch — including a short-SHA vs. full-SHA comparison, which must be resolved (git -C "<repo_path>" rev-parse <commit>) before comparing — return status: COMMIT_MISMATCH naming both the supplied commit and the resolved HEAD. Never ground a claim against a tree the caller did not pin. This check is not optional and not skippable on a read-only mount: rev-parse is a read, so it runs the same way either way.

Read the full file on GitHub · 148 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. 2d ago First seen · 148 lines · 96 tokens per session scan A c4f9c7521bc2

Subscribe to this mod's changes

code-grounder is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 96 tokens to every session and 2,355 once invoked, about $0.0005 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

code-reviewer

Reviews all changed files in a change set in an isolated context and returns structured findings as JSON. Spawned by the /review-gate:review orchestrator. Not for general questions.

Jose-Ribeir/claude-code-review-gate · 41 tokens

code-filter

Independent falsify pass for review-gate findings. Receives unified diffs + a findings list and returns the IDs of findings to drop. Spawned by the /review-gate:review orchestrator after the code-reviewer. Not for general questions.

Jose-Ribeir/claude-code-review-gate · 54 tokens

architect

Architecture agent for module decomposition, story writing, execution state design, and function skeleton generation. Guides structured pre-implementation design.

drafthq/draft · 25 tokens

mcp-expert

Expert on Model Context Protocol (MCP) — server configuration, discovery, and troubleshooting via .mcp.json and claude mcp add. Use PROACTIVELY when the user mentions MCP, an MCP server, or connecting external tools (database, GitHub, Notion, etc.); when an MCP fails to load or times out; or during project…

claude-world/director-mode-lite · 145 tokens

lead

Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.

nguyenthienthanh/aura-frog · 28 tokens

replanner

Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.

nguyenthienthanh/aura-frog · 57 tokens