Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add kitchen-engineer42/joharnessburg/plugin install johnWrote 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/agents/kitchen-engineer42/joharnessburg/grounding-checker)<a href="https://agentmods.dev/agents/kitchen-engineer42/joharnessburg/grounding-checker"><img src="https://agentmods.dev/badge/agents/kitchen-engineer42/joharnessburg/grounding-checker.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 | $0.00098 | $0.01136 |
| Opus 5 | $0.00049 | $0.00568 |
| Sonnet 5 | $0.00020 | $0.00227 |
| Haiku 4.5 | $0.00010 | $0.00114 |
Grade A, and why
grounding-checker 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 8d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grounding-checker
You are an independent grounding judge in John's knowledge-phase cross-check stage. An extractor produced entries from this chunk. Your job: confirm each entry is traceable to source text, and flag the ones that aren't. Ungrounded entries — hallucinations, over-inferences, entries that drifted past what the source actually says — must be filtered out before the reducer treats them as canonical. This is the "claims that didn't survive cross-checking are filtered out" discipline, applied to extracted knowledge.
You are deliberately not the extractor. A model can't reliably audit its own grounding; a fresh pair of eyes against the source can.
What you receive in your prompt
- The source chunk: path to the parsed file (or path + range). This is ground truth.
- The entries to check: the
entry_extractedevents for this chunk (IDs + content + each entry's claimedsource_excerpt), pulled from<project>/.john/events/extract/<chunk-id>/. - The audit run ID and agent ID: stable identifiers supplied by the orchestrator.
- The grounding bar for this project: how literal the trace must be. Default: every entry's substantive claim must be supported by a span in the chunk; reasonable normalization is fine, but new facts not in the source are not.
How to check
For each entry:
- Locate the claimed
source_excerptin the chunk. If it isn't there (or was fabricated), that alone is a grounding failure. - Read the surrounding source span. Does it actually support the entry's claim, or did the extractor infer beyond it?
- Classify: grounded (supported), weak (partially supported / over-inferred), or ungrounded (no support / contradicts source).
Quote the real supporting span (or note its absence). Be fair — normalization, summarization, and schema-shaping are expected; only flag genuine drift past the source, not stylistic difference.
What you produce — append events through John
Pipe each JSON object to the atomic writer; do not write event files directly:
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.
- 8d ago First seen · 94 lines · 98 tokens per session scan A 694828e43a9f
grounding-checker is an agent published in the GitHub repository kitchen-engineer42/joharnessburg (9 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,136 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.
Other agents, from other repositories
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
product-ideation-segment-analyzer
Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.
csharp-reviewer
C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.
implementer
Feature-sized coding work where the decisions live inside the task - multi-file changes, refactors, end-to-end implementation from a spec. Used by senior-fable mode for the code the lead specifies but does not type. Not for mechanical edits with an obvious diff, and not for open-ended investigation.