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 julianobarbosa/claude-code-skills --skill research-reportgit clone --depth 1 https://github.com/julianobarbosa/claude-code-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/julianobarbosa/claude-code-skills/research-report)<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/research-report"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/research-report/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/julianobarbosa/claude-code-skills/research-report"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/research-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 45 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00093 | $0.00897 |
| Opus 5 | $0.00046 | $0.00449 |
| Sonnet 5 | $0.00019 | $0.00179 |
| Haiku 4.5 | $0.00009 | $0.00090 |
Grade A, and why
research-report 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 8d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Report — Summary Report
Reads the JSON files produced by /research-deep and emits a single markdown report at {topic}/report.md.
Trigger
/research-report
Pipeline position
/research-outline → /research-add-* → /research-deep → ► /research-report ◄
Workflow
Step 1 — Locate results directory
Glob */outline.yaml in the current working directory. Read it to get topic and execution.output_dir.
Step 2 — Scan optional summary fields
Read every JSON under output_dir. Collect candidate fields suitable for the table-of-contents column — short, numeric, or scalar metrics. Typical candidates:
github_starsgoogle_scholar_citesswe_bench_scoreuser_scalevaluationrelease_date
AskUserQuestion: "Which of these summary fields do you want next to each item in the TOC?" — present the dynamic list of fields you actually found in this run's JSON files.
AskUserQuestion has a hard cap of four options per question. If you found more than four candidates, either ask twice (covering different field groups), or pick the four most informative-looking candidates yourself and ask the user to confirm or override.
Step 3 — Generate the report script
Write {topic}/generate_report.py. The script's behaviour is specified in references/report-generation-spec.md — read that file before writing the script. It covers JSON shape compatibility, category-name multi-language mapping, complex value formatting, extra-fields collection, uncertain-value skipping, and TOC formatting.
Why the script is regenerated each run instead of bundled as-is: each topic has slightly different field categories and value shapes. Letting the model write the script per run lets it adapt the formatting choices to what the JSON actually contains, while the spec ensures every script meets the same minimum contract.
Step 4 — Execute the script
Run python {topic}/generate_report.py. Check the resulting {topic}/report.md exists and is non-empty; report the path back to the user.
What ships with it
1 file 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.
- 8d ago First seen · 65 lines · 93 tokens per session scan A dfbaab4ad076
research-report is a skill published in the GitHub repository julianobarbosa/claude-code-skills (10 stars, last pushed 16d ago), licensed MIT. It adds 93 tokens to every session and 897 once invoked, about $0.0005 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…