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.
git clone --depth 1 https://github.com/swisstruthorg/swiss-truth-mcpWrote 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/swisstruthorg/swiss-truth-mcp/gsd-debugger)<a href="https://agentmods.dev/agents/swisstruthorg/swiss-truth-mcp/gsd-debugger"><img src="https://agentmods.dev/badge/agents/swisstruthorg/swiss-truth-mcp/gsd-debugger.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 | $0.00029 | $0.10888 |
| Opus 5 | $0.00015 | $0.05444 |
| Sonnet 5 | $0.00006 | $0.02178 |
| Haiku 4.5 | $0.00003 | $0.01089 |
Grade A, and why
gsd-debugger 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 6d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 6d ago First seen · 1,453 lines · 29 tokens per session scan A 9004e7bb9c50
gsd-debugger is an agent published in the GitHub repository swisstruthorg/swiss-truth-mcp (0 stars, last pushed 4mo ago), with no licence file. It adds 29 tokens to every session and 10,888 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.
Other agents, from other repositories
debugger
Diagnose a repeated gate or slice-verify failure via bounded scientific-method hypothesis cycles, auto-invoked before the retry budget is spent.
citizen-entomologist
Curiosity-driven insect guide that celebrates discovery, uses common names alongside scientific names, and channels observations into citizen science platforms like iNaturalist and BugGuide.
ma-process-syntax-consultant
Engage when a process line must be written into a model nobody has inspected — a BSM/UFO name taken from a paper or PDG table, not from the model, aborts at PARSE before any diagram exists; when the model's contents must be looked up, not recalled (display particles/parameters); when one line is re-consumed by a…
valuation-critic
Attacks a finished analysis and reports what breaks. Runs the consistency validator first, then works the red-team sequence — route conformance, bias, single charge per risk, growth paid for, terminal value plausibility, the equity bridge, implied expectations, comparable-set bias, and the seven sins of acquisition…
wiki-lint
Comprehensive wiki health check agent. Scans for orphan pages, dead links, stale claims, missing cross-references, frontmatter gaps, and empty sections. Generates a structured lint report. Dispatched when the user says "lint the wiki", "health check", "wiki audit", or "clean up". Context: User says "lint the wiki"…
perspective_reviewer_agent
Peer Reviewer 3; evaluates cross-disciplinary relevance, broader impact, and alternative interpretations.