forge-extension
Skill2 starsChanged 35 days agoMITView on GitHub
Forge: browser extensions (Chrome/Edge MV3): chrome extension, manifest v3, service worker, content script, permissions, CSP, Web Store, store policy.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- ForgeyClap/Forge-Coreedited, first seen Oct 11, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- ForgeyClap/Forge-Core★ 250% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository74 other files it gives its agents.
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brainstormingSkill
- claude-md-improverSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- forge-agent-reportSkill
- forge-agentSkill
- forge-apiSkill
- forge-botsSkill
- forge-brainstormSkill
- forge-cliSkill
- forge-cmsSkill
- forge-code-reviewSkill
- forge-councilSkill
- forge-dataSkill
- forge-debugSkill
- forge-deeplearnSkill
- forge-docdriftSkill
- forge-doctorSkill
- forge-ecommerceSkill
- forge-electronSkill
- forge-figmaSkill
- forge-fullstackSkill
- forge-gameSkill
- forge-graded-verifySkill
- forge-guardianSkill
- forge-heartbeatSkill
- forge-intakeSkill
- forge-integrationSkill
- forge-mcp-clientsSkill
- forge-migrationSkill
- forge-mindmapSkill
- forge-mlopsSkill
- forge-mobileSkill
- forge-n8nSkill
- forge-nightshiftSkill
- forge-paymentsSkill
- forge-prdSkill
- forge-predictionSkill
- forge-projectbrainSkill
- forge-prompt-coachSkill
- forge-qualitySkill
- forge-ragSkill
- forge-registrySkill
- forge-reportSkill
- forge-routerSkill
- forge-scoutSkill
- forge-scrapingSkill
- forge-scribeSkill
- forge-skill-testingSkill
- forge-snapshotSkill
- forge-verifySkill
- forge-voiceSkill
- forge-websiteSkill
- forge-worktreesSkill
- frontend-designSkill
- grillingSkill
- grill-meSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
No remotely-hosted code (MV3 policy): All executable JS ships inside the package — no eval, new Function on remote strings, or <script src> …
- Very specific: line 16
No secrets in the package; store-policy compliance: No API secret baked into the extension (it's extractable).
- Very specific: line 31
No remotely-hosted code — no eval/new Function/remote <script>.
- Very specific: line 33
Default MV3 CSP kept strict (script-src 'self', no unsafe-eval/unsafe-inline).
- Very specific: line 35
No secrets in the package.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Forge playbook — Browser extension (Chrome MV3)
build-boss leads; security-boss co-owns the permission + messaging + CSP surface (this is a security-heavy domain and a real Codex/security trigger). Popup/options UI defers to forge-website (real content, responsive, a11y); anything that calls a backend defers to forge-integration. Scope is Chrome/Edge Manifest V3 unless the owner asks for Firefox/Safari (those are separate ports). The honesty rule: an extension that "loads unpacked" must have its core flow actually exercised, and every permission requested must be one the code genuinely uses.
Hard rules (non-negotiable)
- Least-privilege permissions. Request only the
permissions+host_permissionsthe code actually uses; preferactiveTabandoptional_permissionsover a blanket<all_urls>. Each permission is justifiable in one sentence. Over-broad scope is both a Web Store rejection risk and a user-trust failure. - No remotely-hosted code (MV3 policy). All executable JS ships inside the package — no
eval,new Functionon remote strings, or<script src>from a CDN. Remote code is a hard Chrome Web Store rejection. - Safe content-script + messaging. Content scripts run in the page's hostile context: validate every
chrome.runtime.onMessagepayload and checksender; never trust orevalwindow.postMessagedata from the page; keepexternally_connectablenarrow.web_accessible_resourcesscoped to specific matches, never<all_urls>. - Strict CSP kept strict. MV3's default extension CSP (
script-src 'self') is not weakened — no'unsafe-eval', no'unsafe-inline', no remote script sources. Sandboxed pages only if genuinely required, narrowly. - Termination-resilient service worker. The MV3 background is an event-driven service worker, not a persistent page: listeners registered at top level, no reliance on in-memory global state surviving, durable state persisted to
chrome.storage. - No secrets in the package; store-policy compliance. No API secret baked into the extension (it's extractable); real secrets sit behind a backend, OAuth via
chrome.identitywith minimal scopes. Single clear purpose, accurate description, privacy disclosure if user data is handled, no obfuscated code.
Team (conditional by stack/level)
Lead: build-boss. Security: security-boss (permission surface, CSP, message validation, no-remote-code — the defining risk of this domain). Support: typescript-reviewer (background/content/messaging code), test-boss (load the unpacked extension in Playwright/Puppeteer for E2E), ui-boss (popup/options UI via forge-website). Backend calls: forge-integration team.
Skills / commands / MCP
Chrome Extension MV3 docs via Context7 (manifest v3, service-worker lifecycle, messaging + storage + identity APIs — get the current API, MV2 patterns are dead). forge-website for the popup/options page UI; forge-integration if it talks to an API; systematic-debugging for service-worker lifecycle bugs (the "why did my listener not fire after idle" class). browser skill / Playwright to load the unpacked build and drive the core flow. No special MCP required. Reuse a bundler (esbuild / Vite / webpack) with an MV3/CRX plugin — don't hand-assemble the package.
Fan-out & flow
L2 a single-purpose extension (popup + one content script); L3 a service worker + multiple content scripts + options page + messaging + a backend. Serial: manifest + permission model → service worker + messaging contract → content scripts → popup/options UI → CSP + security review → load-unpacked E2E → production zip. Parallel: content script ∥ popup/options UI ∥ background logic build in parallel once the message contract is fixed (the message schema is the seam).
Domain gates
- Manifest requests only permissions/
host_permissionsthe code uses;activeTab/optional preferred over<all_urls>(each justified). - No remotely-hosted code — no
eval/new Function/remote<script>; all JS bundled. - Runtime + content-script messages validate
sender+ payload; page-supplied data is nevereval'd;externally_connectableandweb_accessible_resourcesscoped to specific matches. - Default MV3 CSP kept strict (
script-src 'self', nounsafe-eval/unsafe-inline). - Service worker is event-driven and termination-resilient — listeners at top level, durable state in
chrome.storage, no global-state reliance. - No secrets in the package; OAuth via
chrome.identitywith minimal scopes. - Extension loads unpacked and the core flow works (evidence: load + a screenshot/log), and a production zip is produced.
Ship-readiness (unique)
Manifest permissions minimal and each justified; no remote code / eval; messaging validates sender + payload; MV3 CSP strict; service worker termination-resilient (state in chrome.storage); no secrets in the package; extension loaded unpacked with the core flow exercised (real output attached) and a production zip built. Store-listing prerequisites — single-purpose description, privacy policy if user data, per-permission justifications, screenshots — are noted as owner action (submission itself needs a developer account and is owner-gated). Firefox/Safari ports are out of scope unless requested. Advisory checklist; running security-boss / codex-reviewer on the permission + messaging surface is strongly recommended here — not a blocker, but say so if it was not run.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

