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 Mexregkan/claude-for-researchers --skill write-pipelinegit clone --depth 1 https://github.com/Mexregkan/claude-for-researchersWrote 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/mexregkan/claude-for-researchers/write-pipeline)<a href="https://agentmods.dev/skills/mexregkan/claude-for-researchers/write-pipeline"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/write-pipeline/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/mexregkan/claude-for-researchers/write-pipeline"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/write-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 58 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 60 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00121 | $0.01340 |
| Opus 5 | $0.00060 | $0.00670 |
| Sonnet 5 | $0.00024 | $0.00268 |
| Haiku 4.5 | $0.00012 | $0.00134 |
Grade A, and why
write-pipeline 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 12d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/write-pipeline — document the pipeline of any code
The Pipeline/ folder holds one .md per main code describing what it computes and how the code
flows, so future sessions read the map before the (large) source. This skill writes or refreshes
one of those files for a target code. Read Pipeline/README.md first — match its house style.
When is a code "main" enough to document? When it has grown too big to hold in context or read top-to-bottom — the file you dread opening. A 40-line script does not need this; a 300-cell notebook or a multi-pass engine does. That growing-too-big moment is the trigger to run this skill.
When to use
- A load-bearing code has no
Pipeline/*.mdyet (a notebook/engine/script has crossed the "too big to hold in context" threshold, or a new main code was added). - An existing pipeline doc is stale (use
/check-pipelineto detect drift, then this to rewrite). - The user points at a file and says "write its pipeline".
Method (do these in order)
1. Make the code readable. Notebooks are JSON — dump them:
python3 .claude/skills/write-pipeline/dump_code.py \
"$SCRATCH" "path/to/<target>.wb" # .wb/.ipynb → outline+full; .m/.wls/.py printed as-is
$SCRATCH = the session scratchpad. For a notebook this writes <base>.outline.txt (one line per
cell) and <base>.full.txt. Read the outline first, then read the full dump for the cells that
matter. In a .wb cell, kind: 1=markdown, 2=code; the source key is value, language in
languageId (an .ipynb uses source). Plain source files (.m/.wls/.py/…) are read directly.
2. Learn the math/intent from your authoritative notes. Every pipeline file cites the
workbook.tex sections (or paper equations) it implements — the notes are the authority for why,
the code for how. Grep the workbook for the section documenting this code
(grep -n -E '\\(sub)?section' workbook.tex) and read it. Also skim brief.tex and the
CLAUDE.md conventions/status.
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.
- 12d ago First seen · 92 lines · 121 tokens per session scan A 877d2d23702a
write-pipeline is a skill published in the GitHub repository Mexregkan/claude-for-researchers (52 stars, last pushed 8d ago), licensed MIT. It adds 121 tokens to every session and 1,340 once invoked, about $0.0006 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
review-response
Systematic reviewer response workflow: parse comments, classify by severity, develop response strategy, write structured rebuttal. Use when asked to 'write rebuttal', 'respond to reviewers', 'draft review response', or 'handle R&R'.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
goai
GoAI is a Go SDK for AI applications. One unified API across 25+ LLM providers. Inspired by the Vercel AI SDK, adapted to Go idioms (generics, interfaces, channels).