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 tahirzlone/untangle --skill graph-my-taskgit clone --depth 1 https://github.com/tahirzlone/untangleWrote 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/tahirzlone/untangle/graph-my-task)<a href="https://agentmods.dev/skills/tahirzlone/untangle/graph-my-task"><img src="https://agentmods.dev/badge/skills/tahirzlone/untangle/graph-my-task.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.16132 |
| Opus 5 | $0.00047 | $0.08066 |
| Sonnet 5 | $0.00019 | $0.03226 |
| Haiku 4.5 | $0.00009 | $0.01613 |
Grade E, and why
graph-my-task scanned grade E with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
url=$(curl -sS -X POST --data-binary @<path-to-the-file> -H "Content-Type: application/json" https://tahirlone.com/api/untangle/share | node -e "let d='';process.stdin.on('data',c=>d+=c).on('end',()=>{try{const u=JSON.pa Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
url=$(curl -sS -X POST --data-binary @<path-to-the-file> -H "Content-Type: application/json" https://tahirlone.com/api/untangle/share | node -e "let d='';process.stdin.on('data',c=>d+=c).on('end',()=>{try{const u=JSON.pa Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -q '"<name>@' ~/.claude/settings.json .claude/settings*.json 2>/dev/null; echo $? Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
node -e "(async()=>{const B=process.env.UNTANGLE_AIRTABLE_BASE||'appRSePRgk4jlaRUc',T=process.env.UNTANGLE_AIRTABLE_TABLE||'tblOJzSLHAW7lbBWv';let out=[],offset;do{const u=new URL('https://api.airtable.com/v0/'+B+'/'+T); How it starts
The opening of the file, as written. The whole thing — 654 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graph My Task
Turn the user's task description into a vanilla workflow graph: an honest flowchart of how Claude would accomplish the task using ONLY built-in abilities (reasoning, reading/writing files, running commands, browsing if available). Pretend no skills, plugins, connectors, or MCP servers exist.
Rules of decomposition
- Be honest, not flattering. Include the tedious parts: manual data gathering, format wrangling, retry loops after failures, human review gates, copy-paste steps. The pain is the point — the knowledge-base stage below shows how helpers erase it.
- 6–16 nodes. Fewer means you're summarizing; more means you're micro-stepping.
- Exactly one
inputnode (gathering requirements/materials from the user) and at least oneoutputnode (the delivered result). - Node kinds:
input,process,decision(branching judgment),loop(bounded iteration over items),review(human-in-the-loop gate),output. - painLevel rubric (1–5): 1 = trivial/instant · 2 = easy but attention-consuming · 3 = moderate effort or fiddly formatting · 4 = slow, error-prone, or many manual sub-steps · 5 = heavy manual work across multiple tools/sessions.
- Edges:
sequencefor normal flow,branchout of decisions (label each branch),retryfor backward loops (label the failure reason). The graph must be connected; every non-input node is reachable from the input node. - ids are kebab-case (
^[a-z0-9][a-z0-9-]*$), short and descriptive.
ROOT
This skill has two homes: a checkout of its own repository (invoked /graph-my-task), and the installed untangle plugin (invoked /untangle:graph-my-task), where these files live in the plugin's install directory while the working directory is the user's own project. One derivation covers both: ROOT is the directory three levels up from this SKILL.md — SKILL.md → graph-my-task/ → skills/ → .claude/ → ROOT. The harness names this SKILL.md's directory when it loads the skill; derive ROOT from that path, never from where the session happens to be. In a checkout that lands on the repo root; installed as the plugin it lands on a versioned install directory (e.g. …/cache/untangle/untangle/1.0.0/). Wherever <ROOT> appears below, write out that absolute path. schema/, scripts/, and kb/ always resolve from ROOT and never from the working directory — the working directory gets the output file and tier 2's deleted-after scratch, nothing more. And one honest caveat: some harnesses install this SKILL.md alone — no schema/, scripts/, or kb/ beside it — which is survivable: when the ROOT files are missing, the validation ladder, KB tier 2.7, and the hand-over's drop-page fallback below cover every dependency, and nothing else in this skill needs ROOT.
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.
- 7d ago First seen · 654 lines · 94 tokens per session scan E 70f17a155592
graph-my-task is a skill published in the GitHub repository tahirzlone/untangle (2 stars, last pushed 4d ago), licensed MIT. It adds 94 tokens to every session and 16,132 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it E with 4 findings (sends data to an external url, downloads and executes remote code, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
should-i-buy
Helps the user decide on a purchase by taking the product links they're considering, asking a couple of sharp clarifying questions about their needs and circumstances, then opening each link in real Chrome via the Claude-in-Chrome extension to extract price, specs, ratings, reviews, return policy, and shipping.…
emotional-recap
Reviews the user's past Claude Code conversations from a wellbeing perspective — sentiment, tone, emotional arc, recurring patterns — and generates a supportive, science-grounded report in both Markdown and HTML. Default lookback is 48 hours across all projects. Uses recognised emotion frameworks (Plutchik, Ekman…
remarkable-memory
Turns handwritten reMarkable notes into a queryable semantic memory. Syncs pages from a reMarkable tablet (via the reMarkable MCP server, rmapi, or a USB/SSH bridge), renders each page to an image and reads the handwriting with Claude vision — no OCR key — then extracts each page into confidence-scored, human-editable…
skill-creator
Create new Claude Code skills interactively, following all conventions from SKILLSGUIDE.md and the learning/configurability/feedback patterns proven in the best existing skills.
ui-test
Runs UI tests described in plain English by driving real Chrome via the Claude-in-Chrome extension. Covers end-to-end flows (clicks, forms, assertions), visual checks (screenshot + optional baseline diff), accessibility (axe-core), performance (Web Vitals + light Lighthouse-style metrics), and an interactive --debug…
shop-research
Researches products across Amazon, Google Shopping, and relevant specialty sites using the Claude-in-Chrome browser extension. Finds candidates matching user-specified criteria (gift, gadget, gear, home goods, etc.), captures screenshots and key data per candidate, then generates a modern 2026 HTML report with…