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 agentmods add skills/rysh-ai/rysh-cli-code/form-fillernpx skills add rysh-ai/rysh-cli-code --skill form-fillergit clone --depth 1 https://github.com/rysh-ai/rysh-cli-codeWrote 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/rysh-ai/rysh-cli-code/form-filler)<a href="https://agentmods.dev/skills/rysh-ai/rysh-cli-code/form-filler"><img src="https://agentmods.dev/badge/skills/rysh-ai/rysh-cli-code/form-filler.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 | $0.00015 | $0.00359 |
| Opus 5 | $0.00008 | $0.00179 |
| Sonnet 5 | $0.00003 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
form-filler 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 4d 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.
What it actually says
You fill in the form at {{form_url}} with these values, using only the browser (browser_action). Never run shell commands.
Values (one label: value pair per line):
{{field_values}}
Method
- Navigate to {{form_url}} and OBSERVE first: get_elements over the form's
inputs, selects, checkboxes, and buttons. Map each provided label to a
concrete field by its label text, aria attributes, or placeholder —
prefer
aria:/text:selectors over brittle CSS paths. - Fill every mapped field (type / select / check). After each fill, read the field back (get_value) and confirm it holds the intended value.
- If a provided label matches no field, or a required field has no provided value, STOP before submitting and report the mismatch — never invent a value, never leave a required field to luck.
- Submit exactly once. Wait for the result page and read it (get_text).
Report
- submitted: yes/no — and if no, exactly why you stopped.
- The confirmation evidence: quote the success message or describe the result page. If the site shows a validation error instead, quote it verbatim and name the offending field.
- The final mapping used:
form field ← provided labelper line, so a human can audit what went where.
What ships with it
3 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.
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.
- 4d ago First seen · 40 lines · 15 tokens per session scan A b742e609c1f6
form-filler is a skill published in the GitHub repository rysh-ai/rysh-cli-code (5 stars, last pushed 17d ago), licensed Apache-2.0. It adds 15 tokens to every session and 359 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
bureau
Drive Bureau — the browser stack's installable capability server: a stealth Firefox (Camofox) + daemon that exposes browser tools as MCP-over-HTTP on :8830, plus a CLI for saved browser identities (sessions), social capture / search, adapter health probes, declarative workflows, and Guilde connection. Use when working…
browser
Drive the user's REAL authenticated browser (their logins/cookies) via the local-browser chain — guilde → tunnel → daemon → chrome-devtools-mcp → cloned Chrome. The foundation skill for any "do X in a browser as me" task: navigate, capture (element screenshots + selective content/ld+json/readability), inspect network…
x-twitter
Drive the user's authenticated X/Twitter via the browser skill: read timelines/profiles, who-liked/retweeted (Favoriters/Retweeters), search, and gated posts/likes/DMs through X's internal GraphQL API. Use for any 'do X on Twitter/X as me' or build-the-X-graph task.
Drive the user's authenticated Instagram via the browser skill: profiles, media likers/comments, followers/following, search via the web private API; gated like/comment/follow/DM. Use for Instagram research/outreach as the user.
local-browser
Drive the user's real, authenticated Chrome from an agentproto-connected client. Use when a task needs the user's live cookies, sessions, or extensions (Gmail, LinkedIn, GitHub, ad managers, internal tools) rather than a fresh anonymous browser.
youtube
Drive the user's authenticated YouTube via the browser skill: channels, videos, comments + commenters, search via the InnerTube API; gated like/comment/subscribe. Use for YouTube research/automation as the user.