agentmods.dev

research-ingest

research-ingest is a skill for Claude Code, Codex from Encod3d-Sec/TORCH. It costs 51 tokens per session (579 once invoked), scanned A, original, MIT.

A research workflow for adding a CVE report, security advisory, blog post, or GitHub repository to a shared security wiki. It fetches the source, checks whether it was already added, and updates the relevant technique or tool page.

In plain words
What is it for?
Use it to incorporate external security research, payloads, bypasses, vulnerability chains, or tool details into the appropriate wiki pages.
Why use it?
It prevents duplicate research pages and keeps useful findings in the existing knowledge structure instead of scattered source notes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/kali/<name>.

not rated 318repo +30 7d ago A scan 51 tokens original MIT

Good fit Use it to incorporate external security research, payloads, bypasses, vulnerability chains, or tool details into the appropriate wiki pages.

Compare 6 skills from other repositories ↓
View source ↗ Encod3d-Sec/TORCH
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for research-ingest

README.md
[![agentmods](https://agentmods.dev/badge/skills/encod3d-sec/torch/research-ingest/github.svg)](https://agentmods.dev/skills/encod3d-sec/torch/research-ingest)
Your own site
<a href="https://agentmods.dev/skills/encod3d-sec/torch/research-ingest"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/research-ingest/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.

agentmods 80×15 button for research-ingest

Your own site · 80×15
<a href="https://agentmods.dev/skills/encod3d-sec/torch/research-ingest"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/research-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 579 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.00579
Opus 5 $0.00026 $0.00290
Sonnet 5 $0.00010 $0.00116
Haiku 4.5 $0.00005 $0.00058

Measured 9d ago against content hash 5d93f0ed4a98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

research-ingest 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 9d 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.

skills/workflow/research-ingest/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Ingest

Turn an external source (URL or raw/research/ file) into durable wiki knowledge. Synthesise into existing technique/tool pages; do NOT create one page per source. Full workflow: docs/workflows.md (Research ingest / Git repo ingest).

Procedure

  1. Fetch the source.

    • URL: defuddle parse <url> --md for clean markdown (install: npm i -g defuddle); fall back to the WebFetch tool.
    • Local: read the file under raw/research/. GitHub repo: clone via WSL only (wsl -d kali-linux -u kali -- git clone <url> /home/kali/<name>), then read source/README.

  2. Find the home page. qmd_query "<technique/CVE class>" via wiki-search MCP -> identify the technique/tool page that should hold this. One class = one page.

  3. Dedup (skip rule). Read only the target page's frontmatter. If the ingest slug is already in sources:, STOP - already ingested. Otherwise continue.

  4. Synthesise the new payload / bypass / CVE chain / detail into the page's existing sections (Methodology, Key payloads, Bypasses and variants). Add concrete commands in code blocks. Reconstruct any image into a code block - never embed images. No em-dashes.

  5. Tool page if a new standalone tool appears: create/update wiki/tools/<tool>.md.

  6. Record the source. Add the slug to the page's sources: list; bump date_updated. Register URL/path + slug in raw/manifest.md.

  7. Re-index + log. python3 scripts/gen_index.py (catalog) and, after a bulk session, qmd update (search index). Append a one-line entry to session/log.md. Run python3 scripts/lint-wiki.py -q - must be clean.

Guardrails

  • Generic only. Wiki holds reusable methodology; client/engagement specifics stay in targets/<eng>/. Reusable default creds -> wiki/cheatsheets/default-credentials.md; reusable request patterns -> api-request-findings.md.
  • Prefer enriching an existing page over creating a new one. New page only for a genuinely new technique/tool class.

Report: page(s) updated + slug added + lint status.

Read the full file on GitHub · 33 lines

Changes

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.

  1. 9d ago First seen · 33 lines · 51 tokens per session scan A 5d93f0ed4a98

Subscribe to this mod's changes

research-ingest is a skill published in the GitHub repository Encod3d-Sec/TORCH (318 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 579 once invoked, about $0.0003 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.

ResearchSecurity
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens