A documentation-update command for a software repository. It maps changed Go code paths to the documentation pages that may need corresponding updates.

Use it after feature work to inspect changed files and update the related documentation for authentication, runtime, security, tools, memory, scheduling, secrets, channels, and validation.

It reduces the chance that feature changes leave the documentation inaccurate or incomplete. The path mapping helps identify which pages are affected by a code change.

sync-docs — Command by initializ

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/initializ/forge/sync-docs

Clone the repo

git clone --depth 1 https://github.com/initializ/forge

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,533 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01533
Opus 5	$0.00000	$0.00766
Sonnet 5	$0.00000	$0.00307
Haiku 4.5	$0.00000	$0.00153

Measured yesterday against content hash ac89e86ea598, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/sync-docs.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Documentation

After feature work, update the affected documentation to reflect code changes.

Steps

Identify changed files — Run git diff main --name-only to find modified Go files.

Map files to docs — Use this mapping to determine which docs need updates. Paths match the actual docs/ tree (nested under core-concepts/, reference/, security/, deployment/, skills/).

Changed path pattern	Affected docs
`forge-core/auth/`	`docs/security/authentication.md`, `docs/security/audit-logging.md`
`forge-core/runtime/`	`docs/core-concepts/runtime-engine.md`, `docs/core-concepts/hooks.md`
`forge-core/security/`	`docs/security/overview.md`, `docs/security/egress-control.md`
`forge-core/tools/`	`docs/core-concepts/tools-and-builtins.md`
`forge-core/llm/`	`docs/core-concepts/runtime-engine.md`
`forge-core/memory/`	`docs/core-concepts/memory-system.md`
`forge-core/scheduler/`	`docs/core-concepts/scheduling.md`
`forge-core/secrets/`	`docs/security/secret-management.md`
`forge-core/channels/`	`docs/core-concepts/channels.md`
`forge-core/validate/`	`docs/reference/forge-yaml-schema.md`
`forge-cli/cmd/`	`docs/reference/cli-reference.md`
`forge-cli/runtime/`	`docs/core-concepts/runtime-engine.md`
`forge-cli/server/`	`docs/core-concepts/how-forge-works.md`
`forge-cli/runtime/admission_engine.go`, `forge-cli/runtime/admission_loader.go`, `forge-cli/server/admission_middleware.go`, `forge-core/runtime/admission.go`	`docs/security/admission.md` (full operator + platform-integrator reference), `docs/security/audit-logging.md` (`task_admission_denied` event row), `docs/core-concepts/observability-tracing.md` (`admission.check` span attribute table) — keep wire shape, env var names, fail-open semantic, and HTTP 402 response body all in sync
`forge-cli/channels/`	`docs/core-concepts/channels.md`
`forge-cli/tools/`	`docs/core-concepts/tools-and-builtins.md`
`forge-cli/internal/tui/`	`docs/reference/cli-reference.md` (wizard flow)
`forge-plugins/`	`docs/core-concepts/channels.md`, `docs/reference/framework-plugins.md`
`forge-ui/`	`docs/reference/web-dashboard.md`
`forge-ui/handlers_skill_builder.go`, `forge-ui/skill_builder_context.go`, `forge-ui/skill_validator.go`, `forge-ui/static/app.js` (SkillBuilderPage), `forge-cli/cmd/ui_skill_save.go`	`docs/reference/web-dashboard.md` (§ Skill Builder + § Editing an Attached Skill), `docs/skills/writing-custom-skills.md` (§ Iterating from the Skill Builder UI) — keep edit-mode endpoints, prompt-trailer behavior, and overwrite-clears-scripts rule in sync
`forge-skills/`	`docs/skills/writing-custom-skills.md`, `docs/skills/contributing-a-skill.md`
`forge-skills/registry/image-registry.yaml`, `forge-core/packaging/`	`docs/core-concepts/binary-dependencies.md` — refresh the registry contents, install methods, or Dockerfile shape sections; keep the source-file list at the bottom in sync with the actual files touched
`forge-cli/templates/Dockerfile.tmpl`, `forge-cli/build/dockerfile_stage.go`	`docs/core-concepts/binary-dependencies.md` (image-shape section), `docs/deployment/docker.md`
`forge-core/types/` / `forge.yaml`	`docs/reference/forge-yaml-schema.md`
`CHANGELOG.md`	(rendered into release notes; no per-doc sync needed)
Any of `forge-core/`, `forge-cli/`, `forge-ui/`, `forge-plugins/`, `forge-skills/`, `docs/`, `CHANGELOG.md`, `forge.yaml` schema	`.claude/skills/forge.md` — refresh the affected section(s) of the comprehensive knowledge skill. Sweep the specific section that maps to the changed area; don't rewrite the whole file. Keep the table-of-contents anchors in sync with the section headings.
`forge-ui/skill_builder_context.go` (specifically the `skillBuilderSystemPrompt` constant)	`.claude/skills/forge-skill-builder.md` — re-port verbatim. The body must remain byte-identical to the Go constant apart from un-doing the Go string-concatenation escapes (` + "```" + ` → triple-backticks, etc.). Do not edit either side without updating the other.

Read the full file on GitHub · 75 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 75 lines · 0 tokens per session scan A ac89e86ea598

Subscribe to this mod's changes

sync-docs is a command published in the GitHub repository initializ/forge (156 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,533 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Memory and context Security Writing and docs a2a a2a-protocol agent-cli ai-agents ai-agents-cli ai-workforce

04-content-brief

For one priority from contentpriorities.json, generate a content brief with explicit slots for the human expert (founder/domain specialist) to fill with real cases, real data, and real opinions. This is the human-in-loop checkpoint — the moat that prevents the entire workflow from collapsing into "AI writing more…

ViryaZheng/recomby-geo · 96 tokens

01-intake

Build the GEO brand context for a client by ingesting provided materials (PDF/DOCX/PPTX/XLSX, URLs, raw notes) and conducting structured AI-perception + competitor + community research. Writes brandcontext.json validated against schemas/brandcontext.schema.json. Use when starting a new client (clients/ /inputs/ has…

ViryaZheng/recomby-geo · 111 tokens

02-audit

Run a Claude-native visibility audit. For each query in brandcontext.targetqueries, ask Claude to answer the query as a real user would (using WebSearch + WebFetch), then record whether the client brand is mentioned, at what position, and which URLs were cited. Outputs visibilitybaseline.json validated against schema.…

ViryaZheng/recomby-geo · 94 tokens

05-production

Convert an expert-filled brief into a publishable draft. Applies Princeton KDD 2024 GEO techniques (statistics, quotations, citations, authoritative language) to maximize AI citation likelihood. Refuses to run on briefs that haven't been filled by the expert. Outputs drafts/ .md. Use after 04-content-brief produces a…

ViryaZheng/recomby-geo · 74 tokens

06-distribution

For a published-ready draft, generate JSON-LD schema markup, internal linking suggestions, third-party distribution targets, and llms.txt block. Outputs distribution/ .json and distribution/ .publish-bundle.md. Use after 05-production; consumed by 07-reaudit (records actions for attribution).

ViryaZheng/recomby-geo · 63 tokens

07-reaudit

Re-run 02-audit, diff against the previous baseline, attribute movement to specific content/distribution actions. Outputs reaudit/round-N.json validated against attributiondiff.schema.json. This is the closing-of- loop artifact that proves (or disproves) what's actually working. Run monthly after the previous month's…

ViryaZheng/recomby-geo · 70 tokens