01
Cross-tool config
Author rules once, then compile native config layers for the agents your team already uses.
forgekit v0.10.0 · MIT · zero runtime dependencies
-+ forgekit v0.10.0 · + MIT · zero runtime dependencies +
+- Forgekit turns one source of truth into native configuration for AI coding tools, then adds proof-carrying lessons, blast-radius prediction, reuse search, and pre-action guardrails so agents act from shared evidence instead of fresh guesses. + Forgekit turns one source of truth into native configuration for + AI coding tools, then adds proof-carrying lessons, blast-radius + prediction, reuse search, and pre-action guardrails so agents act + from shared evidence instead of fresh guesses.
Platform
The site uses only repository-backed claims: README, CHANGELOG, package metadata, benchmark reports, and optional GitHub API counters on the status page.
+Platform
++ The site uses only repository-backed claims: README, CHANGELOG, + package metadata, benchmark reports, and optional GitHub API + counters on the status page. +
Author rules once, then compile native config layers for the agents your team already uses.
Every durable lesson includes evidence, provenance, confidence, decay, and merge behavior.
Before editing, Forge predicts affected files and tests so agents can plan smaller, safer changes.
Agents are pushed toward existing code paths and prior fixes before inventing another solution.
Scope, assumptions, anchoring, cost, and secret-redaction checks are enforced by CLI hooks.
Knowledge moves with the repository, not with a single chat transcript or vendor workspace.
+ Author rules once, then compile native config layers for the + agents your team already uses. +
++ Every durable lesson includes evidence, provenance, confidence, + decay, and merge behavior. +
++ Before editing, Forge predicts affected files and tests so + agents can plan smaller, safer changes. +
++ Agents are pushed toward existing code paths and prior fixes + before inventing another solution. +
++ Scope, assumptions, anchoring, cost, and secret-redaction checks + are enforced by CLI hooks. +
++ Knowledge moves with the repository, not with a single chat + transcript or vendor workspace. +
+Workflow
-The CLI stays small and dependency-free, while optional live status data is fetched with timeouts, retries, jitter, and HTTP cache validators.
++ The CLI stays small and dependency-free, while optional live + status data is fetched with timeouts, retries, jitter, and HTTP + cache validators. +
Run the installer and generate project-local agent instructions, hooks, and memory stores.
Forge assembles context, reuse candidates, assumptions, scope, and impact predictions before edits.
Tests and human corrections update memory; self-graded claims do not become trusted facts.
+ Run the installer and generate project-local agent + instructions, hooks, and memory stores. +
++ Forge assembles context, reuse candidates, assumptions, + scope, and impact predictions before edits. +
++ Tests and human corrections update memory; self-graded + claims do not become trusted facts. +
+$ forge substrate "Change auth validation and update tests"
✓ loaded team rules from AGENTS.md
✓ found reuse candidates before implementation
@@ -264,12 +836,35 @@ Install once. Gate every meaningful agent action.
- Evidence
Professional, but honest about limits.
- The strongest design choice is restraint: measured numbers are labeled as measured, targets stay targets, and generated pages document their sources.
+
+ Evidence
+
+ Professional, but honest about limits.
+
+
+
+ The strongest design choice is restraint: measured numbers are
+ labeled as measured, targets stay targets, and generated pages
+ document their sources.
+
- ↯Approximate impact atlas
Import-graph predictions are useful for gating and planning, not presented as perfect dependency analysis.
- %Cost claims stay scoped
The page shows the measured routing-stage savings rather than blending measured data with aspirational targets.
+
+ ↯
+ Approximate impact atlas
+
+ Import-graph predictions are useful for gating and planning, not
+ presented as perfect dependency analysis.
+
+
+
+ %
+ Cost claims stay scoped
+
+ The page shows the measured routing-stage savings rather than
+ blending measured data with aspirational targets.
+
+
@@ -279,7 +874,11 @@ Install once. Gate every meaningful agent action.
Data sources
No mock marketing data.
- Every metric and product claim on this site comes from local repository files or the optional public GitHub repository endpoint used by the generated status page.
+
+ Every metric and product claim on this site comes from local
+ repository files or the optional public GitHub repository endpoint
+ used by the generated status page.
+
@@ -296,11 +895,19 @@ No mock marketing data.