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 thedavidweng/skills --skill roast-my-computergit clone --depth 1 https://github.com/thedavidweng/skillsWrote 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/thedavidweng/skills/roast-my-computer)<a href="https://agentmods.dev/skills/thedavidweng/skills/roast-my-computer"><img src="https://agentmods.dev/badge/skills/thedavidweng/skills/roast-my-computer/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/thedavidweng/skills/roast-my-computer"><img src="https://agentmods.dev/badge/skills/thedavidweng/skills/roast-my-computer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Memory Poisoning · line 93 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Excessive Agency · line 135 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00078 | $0.01880 |
| Opus 5 | $0.00039 | $0.00940 |
| Sonnet 5 | $0.00016 | $0.00376 |
| Haiku 4.5 | $0.00008 | $0.00188 |
Grade A, and why
roast-my-computer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roast My Computer
Generate a local-only developer environment roast. Run the deterministic scanner, then write a branded classic-Macintosh-style HTML report using references/HTML_REPORT_FORMAT.md.
Operating rule
Run locally through the executing agent, using the user's filesystem. Treat memory, paths, dotfiles, source code, credentials, scan JSON, and generated reports as private. Secret values must stay redacted.
Workflow
1. Check for existing reports
Before scanning, check the stable report directory for artifacts from a previous run:
REPORT_DIR="${TMPDIR:-/tmp}/roast-my-computer"
mkdir -p "$REPORT_DIR"
ls -t "$REPORT_DIR"/computer-roast-report-*.html 2>/dev/null | head -1
On Windows use %TEMP%\roast-my-computer instead.
If a previous report exists, ask the user:
- Open the existing report — open the most recent HTML file with
open/xdg-open/start. Skip scanning entirely. Done. - Clean up and re-scan — delete all
computer-roast-report-*.htmlandcomputer-roast-scan.jsonin the report directory, then continue to step 2.
If no previous report exists, continue directly to step 2.
2. Pick one scope
Offer only these choices unless the user already chose:
- Project — scan the current working directory. This fits restricted environments that can only read the active repo/workspace.
- Global — let the agent use memory/context to add the user's high-frequency folders, then scan those plus common macOS/Linux/Windows developer locations. Tell the user this is more accurate and may require approving extra filesystem access.
Use Project for "this repo", "current workspace", "safe", or permission-limited runs. Use Global for "my computer", "full roast", "most accurate", or when the user wants the agent to use memory.
3. Build roots
For Project, use the current working directory. Add explicit paths only when the user supplied them.
For Global, first use the agent's memory/context to identify likely user folders: frequent repos, workspaces, design assets, downloads, monorepos, or tool-specific config locations. Then add common defaults from references/DIRECTORY_TARGETS.md.
What ships with it
9 files 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.
- agents/openai.yaml 666 B
- references/DIRECTORY_TARGETS.md 2.1 KB
- references/HTML_REPORT_FORMAT.md 30 KB
- references/PRIVACY_RULES.md 1.7 KB
- references/REPORT_SCHEMA.md 5.8 KB
- references/ROAST_STYLE.md 4.3 KB
- references/ROAST_WRITER_PROMPT.md 7.7 KB
- references/SCORING.md 1.7 KB
- scripts/scan_dev_environment.py 40 KB runs code
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.
- 11d ago First seen · 155 lines · 78 tokens per session scan A eb3df947f46f
roast-my-computer is a skill published in the GitHub repository thedavidweng/skills (11 stars, last pushed 6d ago), licensed MIT. It adds 78 tokens to every session and 1,880 once invoked, about $0.0004 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.