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 CarbeneAI/Forge --skill browsegit clone --depth 1 https://github.com/CarbeneAI/ForgeWrote 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/carbeneai/forge/browse)<a href="https://agentmods.dev/skills/carbeneai/forge/browse"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/browse/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/carbeneai/forge/browse"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/browse.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 | $0.00115 | $0.06085 |
| Opus 5 | $0.00057 | $0.03043 |
| Sonnet 5 | $0.00023 | $0.01217 |
| Haiku 4.5 | $0.00012 | $0.00609 |
Grade A, and why
browse scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://bun.sh/install | BUN_VERSION=1.3.10 bash How it starts
The opening of the file, as written. The whole thing — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
_UPD=$(~/.claude/skills/gstack/bin/gstack-update-check 2>/dev/null || .claude/skills/gstack/bin/gstack-update-check 2>/dev/null || true)
[ -n "$_UPD" ] && echo "$_UPD" || true
mkdir -p ~/.gstack/sessions
touch ~/.gstack/sessions/"$PPID"
_SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
_PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
echo "BRANCH: $_BRANCH"
_SKILL_PREFIX=$(~/.claude/skills/gstack/bin/gstack-config get skill_prefix 2>/dev/null || echo "false")
echo "PROACTIVE: $_PROACTIVE"
echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
echo "SKILL_PREFIX: $_SKILL_PREFIX"
source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
REPO_MODE=${REPO_MODE:-unknown}
echo "REPO_MODE: $REPO_MODE"
_LAKE_SEEN=$([ -f ~/.gstack/.completeness-intro-seen ] && echo "yes" || echo "no")
echo "LAKE_INTRO: $_LAKE_SEEN"
_TEL=$(~/.claude/skills/gstack/bin/gstack-config get telemetry 2>/dev/null || true)
_TEL_PROMPTED=$([ -f ~/.gstack/.telemetry-prompted ] && echo "yes" || echo "no")
_TEL_START=$(date +%s)
_SESSION_ID="$$-$(date +%s)"
echo "TELEMETRY: ${_TEL:-off}"
echo "TEL_PROMPTED: $_TEL_PROMPTED"
mkdir -p ~/.gstack/analytics
echo '{"skill":"browse","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
# zsh-compatible: use find instead of glob to avoid NOMATCH error
for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
if [ -f "$_PF" ]; then
if [ "$_TEL" != "off" ] && [ -x "~/.claude/skills/gstack/bin/gstack-telemetry-log" ]; then
~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true
fi
rm -f "$_PF" 2>/dev/null || true
fi
break
done
If PROACTIVE is "false", do not proactively suggest gstack skills AND do not
auto-invoke skills based on conversation context. Only run skills the user explicitly
types (e.g., /qa, /ship). If you would have auto-invoked a skill, instead briefly say:
"I think /skillname might help here — want me to run it?" and wait for confirmation.
The user opted out of proactive behavior.
If SKILL_PREFIX is "true", the user has namespaced skill names. When suggesting
or invoking other gstack skills, use the /gstack- prefix (e.g., /gstack-qa instead
of /qa, /gstack-ship instead of /ship). Disk paths are unaffected — always use
~/.claude/skills/gstack/[skill-name]/SKILL.md for reading skill files.
If output shows UPGRADE_AVAILABLE <old> <new>: read ~/.claude/skills/gstack/gstack-upgrade/SKILL.md and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If JUST_UPGRADED <from> <to>: tell user "Running gstack v{to} (just updated!)" and continue.
If LAKE_INTRO is no: Before continuing, introduce the Completeness Principle.
Tell the user: "gstack follows the Boil the Lake principle — always do the complete
thing when AI makes the marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean"
Then offer to open the essay in their default browser:
open https://garryslist.org/posts/boil-the-ocean
touch ~/.gstack/.completeness-intro-seen
Only run open if the user says yes. Always run touch to mark as seen. This only happens once.
What ships with it
60 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.
- bin/find-browse 814 B
- bin/remote-slug 572 B
- scripts/build-node-server.sh 1.9 KB runs code
- SKILL.md.tmpl 4.1 KB
- src/activity.ts 6.4 KB runs code
- src/browser-manager.ts 32 KB runs code
- src/buffers.ts 4.2 KB runs code
- src/bun-polyfill.cjs 2.9 KB runs code
- src/cli.ts 25 KB runs code
- src/commands.ts 9.0 KB runs code
- src/config.ts 4.6 KB runs code
- src/cookie-import-browser.ts 23 KB runs code
- src/cookie-picker-routes.ts 8.1 KB runs code
- src/cookie-picker-ui.ts 21 KB runs code
- src/find-browse.ts 1.7 KB runs code
- src/meta-commands.ts 20 KB runs code
- src/platform.ts 634 B runs code
- src/read-commands.ts 13 KB runs code
- src/server.ts 45 KB runs code
- src/sidebar-agent.ts 9.8 KB runs code
- src/sidebar-utils.ts 629 B runs code
- src/snapshot.ts 15 KB runs code
- src/url-validation.ts 3.5 KB runs code
- src/write-commands.ts 14 KB runs code
- test/activity.test.ts 4.4 KB runs code
- test/browser-manager-unit.test.ts 677 B runs code
- test/bun-polyfill.test.ts 2.9 KB runs code
- test/commands.test.ts 77 KB runs code
- test/config.test.ts 13 KB runs code
- test/cookie-import-browser.test.ts 21 KB runs code
- test/cookie-picker-routes.test.ts 7.4 KB runs code
- test/file-drop.test.ts 10.0 KB runs code
- test/find-browse.test.ts 2.0 KB runs code
- test/findport.test.ts 6.2 KB runs code
- test/fixtures/basic.html 914 B
- test/fixtures/cursor-interactive.html 883 B
- test/fixtures/dialog.html 603 B
- test/fixtures/empty.html 43 B
- test/fixtures/forms.html 1.8 KB
- test/fixtures/iframe.html 852 B
- test/fixtures/network-idle.html 974 B
- test/fixtures/qa-eval-checkout.html 4.2 KB
- test/fixtures/qa-eval-spa.html 3.2 KB
- test/fixtures/qa-eval.html 1.7 KB
- test/fixtures/responsive.html 1.4 KB
- test/fixtures/snapshot.html 1.5 KB
- test/fixtures/spa.html 638 B
- test/fixtures/states.html 567 B
- test/fixtures/upload.html 849 B
- test/gstack-config.test.ts 4.7 KB runs code
- test/gstack-update-check.test.ts 21 KB runs code
- test/handoff.test.ts 8.1 KB runs code
- test/path-validation.test.ts 2.2 KB runs code
- test/platform.test.ts 1.0 KB runs code
- test/sidebar-agent-roundtrip.test.ts 7.5 KB runs code
- test/sidebar-agent.test.ts 6.8 KB runs code
- test/sidebar-integration.test.ts 9.8 KB runs code
- test/sidebar-unit.test.ts 3.3 KB runs code
- test/snapshot.test.ts 20 KB runs code
- test/test-server.ts 1.7 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.
- 7d ago First seen · 537 lines · 115 tokens per session scan A 122c5e6573ea
browse is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 6,085 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
web-enumeration
../../../red-team/web-enumeration/SKILL.md.
discovery
Web app discovery — directory/file fuzzing, vhost discovery, JavaScript endpoint extraction.
web-recon
Web application enumeration hub — directory/file fuzzing, vhost discovery, API enumeration, CMS scanning, WAF detection, auth surface mapping, cookie audit.
cookie-audit
Cookie-conditional sink discovery — bisect required cookies per sink, session-write timeline for race-condition challenges.
playwright
Headless Chromium via Playwright (installed pip install playwright && playwright install chromium, with glibc font/nss deps). Use it to interact with JS-heavy apps, complete login/SSO/multi-step flows for an authenticated session, and — critically — to prove client-side findings by observing real execution (an XSS…