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 apply-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/apply-pipeline)<a href="https://agentmods.dev/skills/mexregkan/claude-for-researchers/apply-pipeline"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/apply-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/apply-pipeline"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/apply-pipeline.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 | $0.00000 | $0.01280 |
| Opus 5 | $0.00000 | $0.00640 |
| Sonnet 5 | $0.00000 | $0.00256 |
| Haiku 4.5 | $0.00000 | $0.00128 |
Grade A, and why
apply-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 13d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/apply-pipeline — turn a pipeline (or audit) into code edits
This closes the loop with the other pipeline tools:
| tool | direction | writes? |
|---|---|---|
/write-pipeline |
code → new doc | doc |
/check-pipeline |
code vs doc → drift report | doc (on approval) |
pipeline-auditor (agent) |
code via doc → bug/opt report | nothing (read-only) |
/apply-pipeline |
doc/report → code edits | code (with guards) |
Use it when the user wants the code changed on the basis of the pipeline: implement an optimization the pipeline names, correct code the pipeline (backed by your authoritative notes) shows is wrong, or reconcile code to documented behavior.
Source-of-truth rule (READ FIRST — it decides whether you should edit code at all)
In a research project the code and the committed data are usually ground truth; the pipeline is
a map of intent. So when code and pipeline disagree, the usual fix is to change the doc
(/check-pipeline), NOT the code. Only edit code when one of these holds:
- The user explicitly asks for the code change ("apply this optimization", "make the code do X").
- The pipeline — and the authoritative notes it cites (
workbook.tex/ the paper) — together show the code is genuinely wrong (a real bug), and the user has confirmed they want it fixed. Otherwise, STOP and recommend/check-pipelineinstead. Never "fix" code to match a doc that is itself the thing that's stale.
Method
1. Read the inputs. The pipeline doc, the notes section(s) it cites (grep workbook.tex for the
labels — the authority for why), and, if you're acting on an audit, that report. Dump the code if
it's a notebook: python3 .claude/skills/write-pipeline/dump_code.py "$SCRATCH" "<code>".
2. Pin the exact change. State precisely what will change, in which cells/functions, and why (cite the pipeline line + notes label). Confirm the change preserves the documented behavior (for an optimization: identical output) or corrects it (for a bug: cite the correct form).
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.
- 13d ago First seen · 81 lines · 0 tokens per session scan A d8fa2a1af082
apply-pipeline is a skill published in the GitHub repository Mexregkan/claude-for-researchers (52 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,280 tokens. 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'.
test-iterate-loop
Autonomously diagnose a codebase, apply minimal fixes, and rerun tests until they pass or a real blocker is reached. Use when the user explicitly requests an iterative fix-until-green loop across Python, R, Julia, or HPC workflows.
postmortem
Deliver a structured post-mortem after incidents, mistakes, or stuck sessions. Use when the user requests a structured post-mortem after incidents, mistakes, or stuck sessions.
code-archaeology
Recover the structure, intent, and lineage of old code, data, or analysis files. Use when inherited or dormant research code must be understood before it is changed. Not for a quality review of already-understood code.
devharness
Drive and debug a running app via the devharness MCP server - launch or attach to Chrome and Node.js, set breakpoints and logpoints, inspect call stacks and variables, watch console and network, manage dev servers, replay any earlier tool call by its history index, and record reproduction sequences that verify a fix.…
latex-rescue
Diagnose and fix LaTeX compilation errors. Handles undefined control sequences, missing brackets, math mode violations, package conflicts, undefined references, and environment mismatches.