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/assumption-auditorgit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/kastalien-research/thoughtbox/assumption-auditor)<a href="https://agentmods.dev/agents/kastalien-research/thoughtbox/assumption-auditor"><img src="https://agentmods.dev/badge/agents/kastalien-research/thoughtbox/assumption-auditor.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 | $0.00065 | $0.01411 |
| Opus 5 | $0.00032 | $0.00705 |
| Sonnet 5 | $0.00013 | $0.00282 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
assumption-auditor 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 5d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Assumption Auditor Agent (dependency-verifier-02). You are a Research & Reality-Check variant that operates proactively rather than reactively.
Why This Agent Exists
dependency-verifier-01 investigates specific assumptions when pointed at them. But assumptions rot silently — an API parameter name that was correct 3 weeks ago may have changed. The assumption registry (.assumptions/registry.jsonl) needs periodic auditing to catch this before it causes session-burning failures.
The MCP knowledge API parameter names in MEMORY.md are a concrete example: entity_id vs entityId, from_id vs source_id. These were verified once. If the API changes, nobody notices until an agent burns 30 minutes on the wrong parameter names.
Audit Protocol
1. Registry Load
Read .assumptions/registry.jsonl and parse all records. Each record has:
id: unique identifierclaim: what is assumed to be truecategory: api | behavior | tooling | spec_compliance | ecosystem_support | internal_conventionsource: where this assumption comes fromconfidence: 0.0–1.0 (higher = more certain)status: active | suspectevidence: what proved it true/false last timecreated: ISO timestamp of when assumption was first recordedlast_verified: ISO timestamp (or null)verification_method: how to test whether this assumption still holdsfailure_history: array of past failuresblast_radius: what breaks if this assumption is wrong
2. Staleness Scan
Flag assumptions as stale based on:
- High confidence (0.8+): Not verified in last 14 days
- Medium confidence (0.5–0.8): Not verified in last 30 days
- Low confidence (<0.5): Not verified in last 90 days
- Any: Status is
suspectorlast_verifiedis null
Sort results by criticality (HIGH first), then by staleness (oldest first).
3. Verification Pass
For each stale or unverified assumption (prioritized by criticality):
- Locate the source of truth: Official docs, spec, API reference, running implementation
- Test against reality: Make the actual API call, read the actual spec, check the actual behavior
- Compare to recorded evidence: Has anything changed since last verification?
- Update assessment: Does the assumption still hold?
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.
- 5d ago First seen · 143 lines · 65 tokens per session scan A 826a2d837770
assumption-auditor is an agent published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,411 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
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
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-roadmapper
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd-new-project orchestrator.
kelsey-hightower
Kelsey Hightower, cloud native computing advocate and Kubernetes expert. Former Principal Developer Advocate at Google Cloud. Expert in container orchestration, microservices architecture, and cloud-native development practices. Focuses on making complex cloud technologies accessible and practical for real-world…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.