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 sanjeewamadhuranga/grounding-guard --skill gguard-reportgit clone --depth 1 https://github.com/sanjeewamadhuranga/grounding-guardWrote 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/sanjeewamadhuranga/grounding-guard/gguard-report)<a href="https://agentmods.dev/skills/sanjeewamadhuranga/grounding-guard/gguard-report"><img src="https://agentmods.dev/badge/skills/sanjeewamadhuranga/grounding-guard/gguard-report/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/sanjeewamadhuranga/grounding-guard/gguard-report"><img src="https://agentmods.dev/badge/skills/sanjeewamadhuranga/grounding-guard/gguard-report.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 | $0.00039 | $0.00273 |
| Opus 5 | $0.00019 | $0.00137 |
| Sonnet 5 | $0.00008 | $0.00055 |
| Haiku 4.5 | $0.00004 | $0.00027 |
Grade A, and why
gguard-report 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 12d 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.
What it actually says
Grounding Guard Report
Summarize what Grounding Guard caught.
- Find the session logs:
~/.cache/grounding-guard/sessions/*.jsonl. Each line is one finding event withts,mode,verifier,severity,name,message. Prefer the file matching the current session id if known; otherwise use the most recently modified files (last 24h). - Read the relevant log file(s) and aggregate:
- Total findings by verifier (
packages,imports,gitrefs) and severity (block,warn,info). - List each distinct fabricated reference caught (name + one-line reason).
- Note which were blocking (Claude was forced to self-correct) vs. warnings.
- Total findings by verifier (
- Present a short report:
- Headline count ("Grounding Guard caught N fabricated references this session").
- Table or list of findings.
- If zero findings: say so plainly — that is the desired state.
Do not re-verify anything against registries here; this skill only reports what the hooks already logged.
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.
- 12d ago First seen · 21 lines · 39 tokens per session scan A 33e1c1f8df7b
gguard-report is a skill published in the GitHub repository sanjeewamadhuranga/grounding-guard (1 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 273 once invoked, about $0.0002 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
health-check
Runs plugin health checks (venv packages, skill registration, and album slug collisions). Use when the user asks to check plugin health, verify setup, or troubleshoot missing skills.
verifying-external-behavior
Confirms what a third-party library, remote API, build backend, or scraped document actually does before writing code that depends on it — throwaway probes that run in seconds, permissive clients that forward wrong arguments instead of rejecting them, per-endpoint docs that don't generalize, response shapes that make…
check-failed-run
Diagnoses failed or unstable machine learning training runs across local logs, artifact directories, process targets, experiment trackers, and Vertex AI pipelines. Collects evidence, classifies failure mode, performs root-cause analysis, and delivers a prioritized recovery plan. Run this automatically whenever a…
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…
validate-album
Validates album directory structure, file locations, and content integrity. Use before release or whenever the user wants to check an album's structural health.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.