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 Jamie-BitFlight/claude_skills --skill research-notegit clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote 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/jamie-bitflight/claude_skills/research-note)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/research-note"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/research-note/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/jamie-bitflight/claude_skills/research-note"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/research-note.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00089 | $0.01034 |
| Opus 5 | $0.00044 | $0.00517 |
| Sonnet 5 | $0.00018 | $0.00207 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
research-note 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Note
Synthesize multi-angle research outputs into a single Research section with signal weighting and conflict resolution. Return content to the calling orchestrator — the orchestrator writes to the backlog.
Step 1 — Receive Angle Outputs
Accept the structured report text from each angle that ran:
api-state— API surface, stability, deprecationsecosystem-research— compatibility, dependencies, community healthimpact-measurement— quantitative benchmarks, adoption, performance datacodebase-auditor— behavioral contracts, coding conventions, workflow insertion points, agent data flow maps
Identify and isolate the Gaps section from each report — you will need it in Step 4.
Step 2 — Cross-Angle Signal Detection
For each factual claim that appears in 2 or more independent angle reports, mark it [CROSS-ANGLE].
A claim qualifies when:
- Two angles independently reached the same conclusion from different sources
- Neither angle cites the other's output as its source
Correct: mark [CROSS-ANGLE] only for genuinely independent corroboration. One angle quoting another angle's cited source is not independent corroboration — mark it only in the section of the angle that sourced it independently.
Step 3 — Conflict Detection and Resolution
For each claim where two angles contradict each other, mark it [CONFLICT] and apply the resolution procedure:
- One angle has a primary source citation, the other does not → the cited claim wins. State the resolution explicitly.
- Both angles have citations and still contradict → mark
[UNRESOLVED]and surface it.
Every contradiction must reach a stated resolution or an [UNRESOLVED] marker. Surface all conflicts in the Conflicts section of the output.
Step 4 — Gap Aggregation
Collect the Gaps section from every angle report. Separate into two priority tiers:
- Cross-angle gaps — appear in 2 or more angle reports. Highest priority for follow-up.
- Single-angle gaps — appear in only one angle report.
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 · 103 lines · 89 tokens per session scan A 7922791f4569
research-note is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 1,034 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…