A local community of Claude Code plugins — brand-forge, content-multiplier, green-keeper, money-map, docpin. Most run entirely on your machine; docpin fetches cited version-matched docs and brand-forge's AI imagery is opt-in.
Agent
Plans the asset set for a brand request — decides which assets to produce, their composition and hierarchy, and which engine (vector vs raster) each needs. Use before generating anything ambiguous or multi-asset.
Agent
Visual brand reviewer. Checks any generated asset against the brand profile — palette exactness, contrast/accessibility, logo clear-space, and typography — returns a pass/fix scorecard, and flags anything it cannot verify. Use as the final pass before an asset is delivered.
Agent
Brand and compliance reviewer. Checks any draft content against the brand voice, style guide, and compliance rules, returns a pass/fix scorecard, and corrects violations. Use as the final pass before content is delivered.
Agent
Content strategist. Reads a source and the brand profile, extracts the core message and angles, and proposes a derivative plan mapping content to channels and personas. Use before drafting multi-channel content.
Agent
Verifies that a grounded docpin answer's citations are real — the version matches the lockfile, the URL actually resolves and is version-pinned, and any cited API genuinely appears in that version's docs. Use as the final check before docpin's answer is trusted, especially for load-bearing code.
Agent
Runs docpin's resolve → fetch → distill loop for ONE library in isolation, keeping the multi-step lookup out of the main session's context. Use when the main session needs version-matched docs for a library and you want the fetch/registry-lookup noise kept out of its context.
Agent
Fixes one failing test or type/compile error with the smallest correct change and re-runs to confirm. Applies the anti-fake-green rules. Use to turn a specific red item green.
Agent
Verifies that a fix or new test made something genuinely green and did not cheat. Enforces the anti-fake-green rules and runs revert-verification. Use as the final check before green-keeper reports success.
Agent
Writes or updates a behavioral test for changed code, following test-quality, and verifies the test actually exercises the change. Use to cover new/changed code.
Agent
Analyzes a financial export by running the money-map toolkit — detects the column mapping, categorizes, aggregates, and finds anomalies — then writes a plain-English summary. Never does the arithmetic itself.
Agent
Verifies that reported financial figures are real, computed by the toolkit, and reconcile. Enforces the anti-fabrication rules. Use as the final check before any money-map output is shown.