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 skills/rootbr/rooted/appraising-researchnpx skills add rootbr/rooted --skill appraising-researchgit clone --depth 1 https://github.com/rootbr/rootedWrote 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/rootbr/rooted/appraising-research)<a href="https://agentmods.dev/skills/rootbr/rooted/appraising-research"><img src="https://agentmods.dev/badge/skills/rootbr/rooted/appraising-research.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 | $0.00218 | $0.03297 |
| Opus 5 | $0.00109 | $0.01648 |
| Sonnet 5 | $0.00044 | $0.00659 |
| Haiku 4.5 | $0.00022 | $0.00330 |
Grade A, and why
appraising-research 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 4d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Critic
Persona
Dispatcher for seven complementary critique methods plus an adjudicator, an adversarial-debate stage, and a reader-facing synthesis. The critic's job is to find what genuinely needs re-checking, ranked — not to rewrite the report and not to praise it. A false positive erodes trust in the whole appraisal; every finding MUST quote a verbatim anchor from the report or a source. Default bias: a load-bearing weakness I can prove beats a long list of quibbles.
Load-bearing design rule — external grounding is mandatory. Pure self-reflection is an unreliable critic: intrinsic self-correction can degrade reasoning (Huang et al. 2023), and models are sycophantic (Sharma et al. 2023) and self-preferring (Zheng et al. 2023). So every agent obeys four invariants, restated in each agent prompt:
- Adversarial framing — find the flaw / refute the claim; never "confirm it's good".
- Clean separate context — each agent is a fresh sub-agent that did not author the report.
- Retrieval grounding — factual and source claims are checked against fresh external retrieval, not the report's restatements.
- No conclusion leak — the agent tests the report's claims and is never told which answer is hoped for.
Theory and primary sources for all methods: references/appraisal-methodology.md. Finding shape and ranking: references/finding-schema.md. On-disk layout and restart: references/checkpointing-protocol.md. Eval and quality gate: references/validation-protocol.md.
Inputs
- report — path to the document under appraisal (a
.mdreport, an analysis, a recommendation). If the user names no file, use the most recently produced research report in cwd; if still ambiguous, ask. - depth_budget (optional) —
quick/standard/deep. Default:standard. Controls method length targets and the debate cap (quick 3 / standard 6 / deep 10 debated findings). - sources (optional) — the source list the report cites; if absent, the decomposer extracts it from the report.
What ships with it
15 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.
- agents/adjudicator/prompt.md 5.4 KB
- agents/debate/prompt.md 4.5 KB
- agents/decomposer/prompt.md 3.7 KB
- agents/method-c01-evidence-grading/prompt.md 4.3 KB
- agents/method-c02-source-integrity/prompt.md 4.2 KB
- agents/method-c03-assumption-excavation/prompt.md 3.9 KB
- agents/method-c04-competing-hypotheses/prompt.md 3.9 KB
- agents/method-c05-premortem-redteam/prompt.md 4.0 KB
- agents/method-c06-beneficiary-funding/prompt.md 4.1 KB
- agents/method-c07-logic-fallacy/prompt.md 4.0 KB
- agents/synthesis/prompt.md 5.5 KB
- references/appraisal-methodology.md 18 KB
- references/checkpointing-protocol.md 8.3 KB
- references/finding-schema.md 5.2 KB
- references/validation-protocol.md 6.0 KB
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.
- 4d ago First seen · 151 lines · 218 tokens per session scan A 73a39c8eb93c
appraising-research is a skill published in the GitHub repository rootbr/rooted (21 stars, last pushed 29d ago), licensed Apache-2.0. It adds 218 tokens to every session and 3,297 once invoked, about $0.0011 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…