forge
Skill1 starsChanged 6 months agoMITView on GitHub
Build, audit, deploy, and reason about the Forge + Loom + Crawler substrate. Token-efficient subcommand surface, structured JSON output; reach for these before bash/grep. Use in any tenant or substrate repo. Heavy ops defer to the `forge` MCP server.
78 other projects use a version of this.
Adopted by
Most recently taken up by
- venhdev/skillstheir own version, first seen Nov 8, 2026
- faizanio/FORGEtheir own version, first seen Nov 8, 2026
- jeanchristoph/claude_forgetheir own version, first seen Nov 6, 2026
- pche-broken-artist/forge-of-thoughttheir own version, first seen Nov 6, 2026
- rmkr/skillstheir own version, first seen Nov 5, 2026
- flopperj/dotfiles-coretheir own version, first seen Nov 4, 2026
Used with
Projects with it also use forge-ship, forge-review and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
redteamlifeSkillforge-ship
Use when the user asks to merge, release, promote, reconcile, or close out work in a repo containing `docs/forge/` or governed by FORGE. Not for per-task commits; those complete inside forge-execute-task.
Also in 6 projects that use this
tonmoy007Skillforge-review
Run a multi-dimensional parallel code review over the current change.
Also in 8 projects that use this
weselbenSkillforge-docs
Load before code changes, before writing docs or an ADR, when a user question exposes a missing how-to, and when closing a chunk of work; also loaded by forge after each squash-merge and by deep-research after a report.
Also in 3 projects that use this
DailenGSkillforge-design
Design, UX, and polish discipline for the forge lifecycle. Covers the design tier, the design brief in docs/DESIGN.md, UX requirements and their verification methods, the per-slice design pass, the UX defect register, and the release polish pass. Load whenever work touches a user-facing surface (GUI, terminal, library API, or operated service), whenever a UX observation needs disposing of, and whenever a release is in reach.
Also in 3 projects that use this
DshamirSkillforge-plan
Takes analysis.json + budget cap → derives the full phase sequence, hyperparameters, instance type, cost estimate, and acceptance thresholds. Emits plan.md (the single human gate document) and plan.json (the machine-readable spec that dispatch-v2 consumes). Refuses to plan if estimated cost exceeds budget×1.2.
Also in 4 projects that use this
- tonmoy007Skill
forge-build
Run Stage 6 of the Forge pipeline — implementation. Use when the user says
Also in 3 projects that use this
Other versions78 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 78
- cwinvestments/memstack★ 425same name
- ansari-project/codev★ 298same name
- cluesmith/codev★ 298same name
- swyxio/skills★ 194same name
- simota/agent-skills★ 96same name
- alp82/forge★ 36same name
- TT-Wang/forge★ 34same name
- emiliosheinz/agent-skills★ 20same name
- MetalLegBob/solana-vibes-kit★ 19same name
- kecoma1/MQL5-SKILLS★ 17same name
68 more not listed
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 repository16 other files it gives its agents.
- audit-unused-depSkill
- checkpointSkill
- double-checkSkill
- file-adrSkill
- fleetSkill
- fmt-sweepSkill
- forge-mirror-scaffoldSkill
- gemini-pullSkill
- loop-from-taskSkill
- loop-healthSkill
- loop-onSkill
- loopSkill
- loopsSkill
- regression-guardSkill
- restoreSkill
- workspace-testsSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 3 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 67 edited versions we read keep these.
3
Distinctive
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 8
Use when working in any tenant repo (~/projects/<Name>/) or substrate repo (~/projects/PlausiDen-Forge, PlausiDen-Loom, PlausiDen-Crawler).
- Very specific: line 13
Prefer its typed tools over shelling forge — structured JSON, no CLI re-parse, schemas lazy-load so context cost is per-tool-called.
- Very specific: line 22
Every session that touches the substrate runs forge orient (tool or CLI) before anything else — it enumerates doctrine rules in scope, the …
- Very specific: line 58
Add a Loom primitive (typed CmsSection / CmsBlock variant), or
- Distinctive: line 59
Add a Forge phase / gate, or
- Distinctive: line 65
Don't bash/grep when a Forge subcommand/tool exists.
- Very specific: line 66
Don't add a new section primitive when atomic CmsBlock composition suffices (doctrine prim-012 rejects one-tenant-shaped premades — …
- Distinctive: line 67
Don't bake tenant identity into substrate Rust or commit messages — substrate stays generic.
“Common” is measured: kept by at least 6 in 10 of the 67 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/forge — PlausiDen-Forge substrate operations (MCP-backed)
Use when working in any tenant repo (~/projects/<Name>/) or substrate repo
(~/projects/PlausiDen-Forge, PlausiDen-Loom, PlausiDen-Crawler).
Prefer the forge MCP server
Forge ships as the forge MCP server (forge-mcp, registered with Claude).
Prefer its typed tools over shelling forge — structured JSON, no CLI re-parse,
schemas lazy-load so context cost is per-tool-called. ~21 tools incl.
forge.orient, forge.build, forge.audit*, forge.doctrine.for,
forge.codegen, forge.synthesis.preview, forge.manifest.validate,
forge.docs.query, forge.resumption_brief, forge.canonical_tasks,
forge.bricks, forge.budgets, forge.exemplars. Shell fallback:
~/projects/PlausiDen-Forge/target/release/forge <cmd>.
Orientation FIRST
Every session that touches the substrate runs forge orient (tool or CLI)
before anything else — it enumerates doctrine rules in scope, the skills
inventory, canonical defaults (axum / tokio / sqlx / maud / serde-deny-unknown /
Ed25519 + ML-DSA / clap / anyhow-thiserror / proptest / tracing), anti-patterns,
and next-step commands. It replaces 5–10 file reads.
Tenant model
PlausiDen-Forge/— substrate ONLY (Rust crates, phases, docs). Nocms/*.json, nostatic/assets/*.~/projects/<Tenant>/— per-tenant repo:cms/index.json,static/assets/*,forge.toml, optionalvariables.json/palette.json/site.json.- Build a tenant:
cd ~/projects/<Tenant> && forge build --root .
Subcommand cheat-sheet
| Command | What | When |
forge orient | Session brief | First action |
forge build --root <tenant> | Run every phase against the tenant | After CMS/substrate edits |
forge build --json-report <path> | Structured build report | Parsing findings programmatically |
forge audit <phase> [--explain] | One-off scan (+ why it fires / how to fix) | Pre-commit, ad-hoc, clearing a strict |
forge authoring | Flag empty / below-floor content fields | Before declaring a tenant authored |
forge synthesis preview | Preview a SiteSpec before generating cms/ | Designing a tenant from spec |
forge codegen | Emit a self-contained axum+tokio+sqlx crate from cms/ | Static build needs server handlers |
forge doctrine for <path> [--terse] | Applicable rules (terse = citation-ready) | Cite rules in PRs |
forge fix | Auto-fix mechanical findings from latest report | After a build with fixable findings |
Shipped tenant-style surface (as of 2026-06)
forge.toml [style.*] drives rendering without hand-authored CSS:
palette / fonts / radius / density, plus [style.nav|image|weights|sizes|text]
CSS-var hooks and self-hosted [[style.webfonts]]. Tenant overrides emit as an
external, SRI-pinned /tenant-style.css (CSP style-src 'self' — inline is
blocked). [render] clean_urls=true → extensionless routing; <root>/site.json
→ site-wide shared chrome (nav/footer/brand). {{ VAR }} / @asset-slug
substitution from variables.json / assets-map.json is live.
Substrate-vs-tenant discipline (ABSOLUTE)
Hand-coding HTML / CSS / JS in tenant repos is forbidden — forge build flags it
via substrate_purity. Every gap is a substrate change:
- Add a Loom primitive (typed
CmsSection/CmsBlockvariant), or - Add a Forge phase / gate, or
- Extend doctrine.
Tenant authoring goes through
CmsSectionpremades orCmsSection::Compose+ atomicCmsBlockprimitives (text/heading/image/link/spacer/divider/container/row/column).
Don't
- Don't bash/grep when a Forge subcommand/tool exists.
- Don't add a new section primitive when atomic
CmsBlockcomposition suffices (doctrineprim-012rejects one-tenant-shaped premades — generalize to variants/config). - Don't bake tenant identity into substrate Rust or commit messages — substrate stays generic.
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.