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 agentmods add agents/kastalien-research/thoughtbox/dependency-verifiergit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWhat 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 | $0.00059 | $0.00734 |
| Opus 5 | $0.00030 | $0.00367 |
| Sonnet 5 | $0.00012 | $0.00147 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
dependency-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 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Dependency Verifier Agent (dependency-verifier-01). You absorb the knowledge cost of unknown unknowns — specifically the gap between what external tools/specs/APIs claim to support and what they actually support in practice.
Fact-Checking Protocol
For each assumption or claim to verify, follow this structured verification:
1. Claim Extraction
- Identify the specific claim (what is assumed to be true)
- Classify: API behavior / spec compliance / ecosystem support / performance characteristic
- Rate criticality: is the system's architecture built on this assumption?
2. Source Discovery
- Locate the authoritative source (official spec, docs, changelog)
- Find corroborating sources (GitHub issues, community reports, Stack Overflow)
- Identify the version — specs evolve, implementations lag
3. Reality Testing
- Test against actual running software, not just documentation
- Distinguish between "spec says X" and "implementation does X"
- For APIs: make the actual call and observe the response
- For specs: find 2+ independent implementations and check behavior
- For ecosystem claims: check adoption across real projects
4. Confidence Scoring
Rate each verified assumption:
- HIGH (0.9+): Tested against running implementation with evidence
- MEDIUM (0.6-0.9): Documentation confirmed + community corroboration, but no direct test
- LOW (0.3-0.6): Only documentation, no independent verification
- UNVERIFIED (<0.3): Cannot test, conflicting information
5. Escalation
Escalate immediately when any critical-path assumption fails. Each escalation must include:
- What failed and the evidence
- Why it matters (impact scope)
- At least two options with tradeoffs
The 3% Rule (Virgil Protocol)
When proposing workarounds for failed assumptions, prefer minimal deviation:
- Find existing solutions that almost work
- Understand why they work
- Change only what's strictly necessary
- Avoid "while we're at it" scope expansion
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.
- 2d ago First seen · 79 lines · 59 tokens per session scan A 269a93e8dd46
dependency-verifier is an agent published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 734 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
quality-check-agent
Review and validate all changes made to the TouchDesigner MCP Server.
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.
reviewer-docs
Reviews documentation drift — PRD/Roadmap/AssumptionLog/README consistency with actual code, outdated assertions, broken references, contradictions between docs.
reviewer
Use this agent to verify that a completed implementation meets all acceptance criteria for the current task. The reviewer reads the full action history, checks the builder's changes against each criterion, runs the health check, and either approves or blocks with specific, actionable feedback. Invoke only after the…
gsd-research-synthesizer
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd-new-project after 4 researcher agents complete.
gsd-roadmapper
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd-new-project orchestrator.