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 nirecom/agents --skill save-researchgit clone --depth 1 https://github.com/nirecom/agentsWrote 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/nirecom/agents/save-research)<a href="https://agentmods.dev/skills/nirecom/agents/save-research"><img src="https://agentmods.dev/badge/skills/nirecom/agents/save-research/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/nirecom/agents/save-research"><img src="https://agentmods.dev/badge/skills/nirecom/agents/save-research.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 | $0.00020 | $0.00632 |
| Opus 5.5 | $0.00008 | $0.00253 |
| Sonnet 5.5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
save-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 21d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save research findings from the current conversation to a persistent research-results file.
Procedure
SR-1. Identify findings: Review the current conversation for research results worth preserving.
If no research has been conducted yet, tell the user and stop.
SR-2. Determine filename: Use the argument as the filename slug (kebab-case .md).
If no argument was given, derive a slug from the research topic.
SR-3. Check for duplicates: Read ../my-specs-repo/projects/engineering/research-results/
to see if a file on the same topic already exists.
- If it exists, propose updating the existing file instead of creating a new one. SR-4. Draft the document in chat using this template:
# <Title>
Date: <YYYY-MM-DD>
Motivation: <why this research was needed — the question or decision it informed>
## Background
<context that motivated the investigation>
## Key Findings
### 1. <Finding>
<summary>
**Sources:**
- <URLs>
### 2. <Finding>
...
## Applied Analysis
<how findings apply to the project — tables, trade-offs, recommendations>
## Conclusion
<actionable conclusion with numbered rationale>
SR-5. Wait for user approval before writing the file.
SR-6. Write the file to ../my-specs-repo/projects/engineering/research-results/<slug>.md.
SR-7. Commit: Run git -C ../my-specs-repo add and git -C ../my-specs-repo commit for the new file.
This commit is to a separate repository (my-specs-repo). It is NOT the main project commit
and must NOT trigger USER_VERIFIED or advance the calling workflow step.
SR-8. Return to caller: After the commit, explicitly state which workflow step to resume
(e.g., "save-research complete. Resuming the research workflow step.") and do not mark
any workflow phase as complete.
Rules
- Never set USER_VERIFIED after this skill — this is an auxiliary tool called mid-workflow. Completing save-research does not constitute completion of the calling workflow step.
- Do not modify any files in the current project — output goes to my-specs-repo only
- Always include source URLs for traceability (no URLs = not worth saving)
- Content language: Japanese (my-specs-repo is a private repository)
- Follow the established format from existing files in research-results/
- Strip conversation-specific noise — save only the reusable knowledge
- Do not save trivial findings that are easily re-discoverable via a single web search
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.
- 21d ago Changed · -1 lines 2e2d1f5229de
- 1mo ago First seen · 72 lines · 20 tokens per session scan A 8373d18824db
save-research is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 632 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…