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 Mburdo/knowledge_and_vibes --skill resolvegit clone --depth 1 https://github.com/Mburdo/knowledge_and_vibesWrote 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/mburdo/knowledge_and_vibes/resolve)<a href="https://agentmods.dev/skills/mburdo/knowledge_and_vibes/resolve"><img src="https://agentmods.dev/badge/skills/mburdo/knowledge_and_vibes/resolve/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/mburdo/knowledge_and_vibes/resolve"><img src="https://agentmods.dev/badge/skills/mburdo/knowledge_and_vibes/resolve.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 | $0.00042 | $0.02064 |
| Opus 5.5 | $0.00017 | $0.00826 |
| Sonnet 5.5 | $0.00008 | $0.00413 |
| Haiku 4.5 | $0.00004 | $0.00206 |
Grade A, and why
resolve 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 1mo 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve — Test-Based Adjudication
Test-based adjudication for multi-agent or multi-approach disagreements.
Design rationale: This skill uses the orchestrator-subagent pattern because test-based adjudication involves substantial cognitive work: position gathering, discriminating test design, test execution, and evidence-based adjudication. Each phase benefits from fresh context to prevent anchoring bias. See
docs/guides/ORCHESTRATOR_SUBAGENT_PATTERN.md.
When This Applies
| Signal | Action |
|---|---|
| Multiple agents disagree | Run full protocol |
| Multiple valid approaches | Run full protocol |
| User asks "which approach" | Run full protocol |
| Architectural decision needed | Run full protocol |
| User says "/resolve" | Run full protocol |
Philosophy
"Tests are the medium of disagreement, not rhetoric." — DebateCoder
Research backing:
research/003-debate-or-vote.md: Voting beats extended debateresearch/041-debatecoder.md: Tests adjudicate better than argumentsresearch/042-rankef.md: Selection beats unguided reasoning
Key principles:
- Tests decide, not rhetoric
- Max 2 discussion rounds without tests
- Preserve dissent for user decision when tests don't discriminate
- No compromise—evidence picks winner
Tool Reference
File Operations
| Tool | Purpose |
|---|---|
Read(context_paths) |
Read relevant code/docs |
Write(file_path, content) |
Write position/test reports |
Grep(pattern) |
Search codebase for patterns |
Testing
| Command | Purpose |
|---|---|
pytest tests/... |
Run discriminating tests |
npm test |
Run JS/TS tests |
Discriminating Tests
A discriminating test is one where:
- Position A passes, Position B fails (or vice versa)
- It directly tests the contested claim
- Result is observable and repeatable
Decision Outcomes
| Outcome | When | Action |
|---|---|---|
| Clear winner | Tests discriminate (2-1 or better) | Document decision |
| No winner | Tests don't discriminate | Preserve dissent, ask user |
| Value tradeoff | Equal test results | Present options to user |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 283 lines · 42 tokens per session scan A f3cfd1ca22bb
resolve is a skill published in the GitHub repository Mburdo/knowledge_and_vibes (44 stars, last pushed 9mo ago), licensed MIT. It adds 42 tokens to every session and 2,064 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.