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 pioneerdotai/pioneer --skill browsergit clone --depth 1 https://github.com/pioneerdotai/pioneerWrote 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/pioneerdotai/pioneer/browser)<a href="https://agentmods.dev/skills/pioneerdotai/pioneer/browser"><img src="https://agentmods.dev/badge/skills/pioneerdotai/pioneer/browser/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/pioneerdotai/pioneer/browser"><img src="https://agentmods.dev/badge/skills/pioneerdotai/pioneer/browser.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00042 | $0.01730 |
| Opus 5.5 | $0.00017 | $0.00692 |
| Sonnet 5.5 | $0.00008 | $0.00346 |
| Haiku 4.5 | $0.00004 | $0.00173 |
Grade A, and why
browser 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 3d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pioneer Browser
Drive a browser with agent-browser through the runtime's available command
execution tool. Ordinary navigation, reading, interaction and capture can start
from this file. Load detailed references only for the matching task.
Runtime binding
In native Pioneer, load this skill by its exact skill:<id> reference and resolve
package files under the returned skill_asset_root. In Codex, Claude and
OpenCode, resolve files relative to the exported skill directory (the Pioneer
system alias is pioneer-system-browser). Use only tools in the current catalog;
the skill does not supply tools or extend permissions.
Run an installed agent-browser directly. Do not repeat installation or setup
checks before ordinary commands. If it is missing or a browser launch fails,
read setup and troubleshooting.
Prefer an available service connector when it supports the requested operation.
Select a task session
Use one named session unique to this task or turn. Include the task/turn id or a fresh nonce; a domain or worktree alone collides with other Pioneer agents. Give independent workers their own suffixes. Keep the actual name in working notes so it survives compaction.
Pass --session <actual-name> on every command across separate tool calls.
Alternatively set AGENT_BROWSER_SESSION in each execution environment;
an export in one shell call may not survive the next. All bare commands in
references assume that environment is set. Reuse a prior session only when
continuing that task or deliberately reusing authorized saved state.
Core workflow
Replace the example session suffix with this task's unique id:
browser_session="pioneer-browser-<unique-task-or-turn-id>"
agent-browser --session "$browser_session" open https://example.com
agent-browser --session "$browser_session" snapshot -i
# Choose refs from the actual snapshot, then act:
agent-browser --session "$browser_session" click @e3
# Wait for the expected result, then inspect it:
agent-browser --session "$browser_session" wait --text "Expected result"
agent-browser --session "$browser_session" snapshot -i
What ships with it
30 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.
- LICENSE 11 KB
- NOTICE 484 B
- references/agentcore.md 6.2 KB
- references/authentication.md 8.7 KB
- references/commands.md 35 KB
- references/core.md 11 KB
- references/derive-client.md 8.1 KB
- references/dogfood.md 8.4 KB
- references/electron.md 7.5 KB
- references/issue-taxonomy.md 4.6 KB
- references/profiling.md 3.9 KB
- references/protected-vercel-deployments.md 7.5 KB
- references/proxy-support.md 5.1 KB
- references/session-management.md 7.3 KB
- references/setup-and-troubleshooting.md 6.6 KB
- references/slack-tasks.md 9.1 KB
- references/slack.md 7.6 KB
- references/snapshot-refs.md 4.8 KB
- references/streaming.md 9.1 KB
- references/tools-and-runtime.md 6.8 KB
- references/trust-boundaries.md 4.3 KB
- references/vercel-sandbox.md 11 KB
- references/video-recording.md 4.9 KB
- references/webgpu.md 7.2 KB
- references/webmcp-gen.md 5.4 KB
- templates/authenticated-session.sh 6.2 KB runs code
- templates/capture-workflow.sh 5.7 KB runs code
- templates/dogfood-report-template.md 2.2 KB
- templates/form-automation.sh 6.1 KB runs code
- templates/slack-report-template.md 3.0 KB
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.
- 3d ago Changed · -291 lines · +16 tokens per session scan D → A ce02d67cf8a6
- 2mo ago First seen · 429 lines · 26 tokens per session scan D 34b83c3b9700
browser is a skill published in the GitHub repository pioneerdotai/pioneer (22 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,730 once invoked, about $0.0002 per session on Opus 5.5. 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
XSS_SKILL
Cross-site scripting skill vision validation.
core-agent-browser
Internal support skill for agent-browser CLI workflows used by rust-learner, docs-researcher, and crate-researcher. Use only when browser automation is explicitly required.
rag-synthesize
RAG synthesis prompt for axon ask — source-grounded, depth-adaptive, injection-hardened. Embedded by crates/axon-services/src/query/synthesis/prompt.rs and provisioned to the isolated Gemini runtime by axon-llm.
axon-snippets
Use when discovering, reviewing, installing, or running reusable Labby Code Mode snippets for Axon search, source indexing, research, extraction, monitoring, QA evidence, and the workflow skills planned for retirement.
using-axon
Use when operating an installed Axon through its MCP tool or CLI to search, index sources, query the corpus, extract data, manage jobs or watches, and troubleshoot the RAG stack. For first-time setup or deployment repair, use install-axon.
install-axon
Use when installing or repairing Axon, choosing Incus or systemd, configuring bearer/OAuth auth, exposing MCP, selecting Codex app-server synthesis, connecting an agent, or verifying the RAG stack.