forge
Search, bind, validate, and certify entries of the Forge, the catalog of certified reusable building blocks (shared services, libraries, templates, interface…
Skill by ALTEN-group
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/alten-group-forge
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 4
alten-group.github.io· found in codecodeload.github.com· found in install commandgatelin.fr· found in codegithub.com· found in code
Files it touches
~/.claude/skills/forge
What's inside
- Skill name
forge- Description
- Search, bind, validate, and certify entries of the Forge, the catalog of certified reusable building blocks (shared services, libraries, templates, interface contracts). Ships a seed catalog with Gatelin and Foxnox. Use when Think looks for assets to reuse before a custom build, when CI checks Forge bindings in think.md and plan.md, when a proposed asset is added to the catalog, or when reporting Forge health.
- License
- MIT
- Instructions
- 55 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (14)
- SKILL.md
- catalog.json
- forge-contract.md · references/
- bindings-check.mjs · scripts/
- bindings-check.test.mjs · scripts/
- catalog-lib.mjs · scripts/
- catalog-lib.test.mjs · scripts/
- discover.mjs · scripts/
- discover.test.mjs · scripts/
- forge-fixture.mjs · scripts/
- forge-health.mjs · scripts/
- forge-health.test.mjs · scripts/
- validate-forge.mjs · scripts/
- validate-forge.test.mjs · scripts/
SKILL.md (first lines)
# Forge Deterministic tooling around the Forge catalog: discover candidates for a need, validate the catalog against the certification rules, check Forge asset bindings in Think and Plan records, and report health signals. AI discovers and drafts. The Architect certifies and owns the Forge. ## When to Use This Skill - Think must search for reusable assets before choosing a custom build, and record the chosen assets as bindings. - CI must gate the bindings in `think.md` (and their use in `plan.md`) against the catalog. - A new or changed asset is proposed for the catalog and must meet the certification checklist. - The Architect wants Forge health signals across the work items. ## Path resolution Resolve `references/`, `scripts/`, and `catalog.json` relative to **this skill's install directory** (the folder that contains this `SKILL.md`), not the consumer repository root or the current shell cwd. If the skill was installed under `.agents/skills/forge/` or `.claude/skills/forge/`, use that base path. ## Workflow 1. **Read `references/forge-contract.md` now.** It is the authoritative source for the catalog resolution order (`--catalog`, `FORGE_CATALOG`, then the seed `catalog.json`), the asset schema, certification checklist, lifecycle, binding format, and health signals. The seed lists **Gatelin** and **Foxnox**. An organization points `FORGE_CATALOG` at its own catalog. 2. **Discover** (Think). Search the catalog for the need, then judge the candidates semantically against their capabilities and interface docs: ```bash node scripts/discover.mjs --need "users sign in with JWT sessions and role based access" [--kind shared-service] [--limit 5] [--json] ``` 3. **Bind** in `think.md` under `## Forge Asset Bindings` as `- **forge/<id>@<version>:** <how it is composed>`. A custom build states `- **None:** <reason>` and a `Custom Build Reason` that names what was searched. Then check: ```bash node scripts/bindings-check.mjs --think specs/issue-42/think.md # after Plan: every bound asset must be composed by at least one step node scripts/bindings-check.mjs --think specs/issue-42/think.md --plan specs/issue-42/plan.md ``` 4. **Compose** in Plan and Code: the steps import, call, or deploy the bound asset, following its integration guide. Do not re-implement what it offers. 5. **Certify** a proposed asset (Architect decides): draft the catalog entry, then validate the catalog in the pull request: ```bash node scripts/validate-forge.mjs --catalog forge-catalog.json ``` 6. **Report health** (Architect, periodic): ```bash node scripts/forge-health.mjs --catalog forge-catalog.json --specs specs [--stale-days 180] ``` Treat a nonzero exit as invalid output and fix the file rather than ignoring errors. Warnings (stale binding, alpha or beta maturity, a custom build that matches a Forge asset) need an answer in the Think record, not silence. ## Done When - `bindings-check.mjs` exits 0 for the Think record, with every warning answered in `Reasoning` or `Custom Build Reason`. - Every binding names an asset and version that exist in the catalog, and none is deprecated or removed. - A catalog change passes `validate-forge.mjs` and is merged by the Architect through a pull request. - No asset in the catalog or in a binding was invented.
From ALTEN-group/coding-pal, MIT.
More from ALTEN-group/coding-pal
- 0.624score
angular-admin-examples
ALTEN-group
Scaffold or match Angular admin CRUD entity slices (model/conf/service, thin feature component, protected routes, resolvers).
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
incident-record
ALTEN-group
Author and validate incident records (docs/incidents/<date>-<slug>.md): detect, mitigate first, diagnose with correlated evidence, repair with a failing test…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
learn-signals
ALTEN-group
Close the Learn loop: turn validated incident records, invalidated hypotheses, and high severity telemetry findings into Triage backlog issue bodies (labels…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
meeting-pack
ALTEN-group
Structure, validate, and hand off persistent Meeting Packs from client meeting transcripts: normalize a plain-text transcript, build a pack (summary…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
migration-docs
ALTEN-group
Structure, author, and validate the migration documentation set (assessment.md, migration-plan.md, runbook.md) for moving an application from one…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
mutation-bar
ALTEN-group
Gate a change on its Mutation Testing Bar: read a Stryker mutation-testing-elements JSON (or a generic killed/survived summary), compute the mutation score…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
code-loop
ALTEN-group
Drive the Code stage one plan step at a time with persistent progress, enforce the fix-loop limit, and guard agent branches.
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
context-health
ALTEN-group
Check the health of Persistent Context and prepare the weekly Persistent Context & Controls review: lint instruction files (missing description, broad…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
contract-compat
ALTEN-group
Classify the differences between two OpenAPI 3.x JSON documents (or two JSON Schemas, with local $ref resolved) as BREAKING or compatible, and fail on any…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
control-guard
ALTEN-group
Fail a change that weakens a deterministic control (deleted or skipped tests, lowered thresholds, disabled workflow steps, edited control files, added…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
criteria-verify
ALTEN-group
Prove that every acceptance criterion (AC-<n>) in a plan.md has at least one passing test and that no test mapped to a criterion failed, by reading JUnit XML…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
decision-record
ALTEN-group
Structure, draft, validate, and track the Architect's decision records (docs/decisions/NNNN-slug.md) and escalations with a default date.
SkillAFreshness: A★ 5Claude Code +9
Signals
- Stars
- 5
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 13, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ALTEN-group/coding-pal
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ALTEN-group
- 0.624score
angular-admin-examples
ALTEN-group
Scaffold or match Angular admin CRUD entity slices (model/conf/service, thin feature component, protected routes, resolvers).
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
control-guard
ALTEN-group
Fail a change that weakens a deterministic control (deleted or skipped tests, lowered thresholds, disabled workflow steps, edited control files, added…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
context-health
ALTEN-group
Check the health of Persistent Context and prepare the weekly Persistent Context & Controls review: lint instruction files (missing description, broad…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
contract-compat
ALTEN-group
Classify the differences between two OpenAPI 3.x JSON documents (or two JSON Schemas, with local $ref resolved) as BREAKING or compatible, and fail on any…
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
code-loop
ALTEN-group
Drive the Code stage one plan step at a time with persistent progress, enforce the fix-loop limit, and guard agent branches.
SkillAFreshness: A★ 5Claude Code +9 - 0.624score
criteria-verify
ALTEN-group
Prove that every acceptance criterion (AC-<n>) in a plan.md has at least one passing test and that no test mapped to a criterion failed, by reading JUnit XML…
SkillAFreshness: A★ 5Claude Code +9
Cite this page
forge skill. Agent Mart. https://agentmart.dev/skills/alten-group-forge (last updated 2026-10-24)