Skip to content

Wolfe-Jam/claude-faf-mcp

v5.8.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agents-md ai ai-context ai-readiness anthropic claude
+14 more
claude-ai claude-desktop developer-tools faf gemini github-copilot mcp mcp-server model-context-protocol nodejs npm project-dna typescript vscode

Summary

AI summary

Native SessionStart hook (--session-refresh) added for fresh context per session.

Changes in this release

Feature Low

Adds Native SessionStart hook (`--session-refresh`) for fresh context heartbeat.

Adds Native SessionStart hook (`--session-refresh`) for fresh context heartbeat.

Source: llm_adapter@2026-06-11

Confidence: high

 —
Feature Low

Adds `faf_setup` tool (#35) to install, preview, confirm, or remove faf hook.

Adds `faf_setup` tool (#35) to install, preview, confirm, or remove faf hook.

Source: llm_adapter@2026-06-11

Confidence: high

 —
Feature Low

Adds determinism parity hash (`faf_score`/`faf_trust`) for engine‑agnostic verification.

Adds determinism parity hash (`faf_score`/`faf_trust`) for engine‑agnostic verification.

Source: llm_adapter@2026-06-11

Confidence: high

 —
Feature Low

Adds the ✪ trust receipt artifact, a render‑identical self‑verifying score+parity record.

Adds the ✪ trust receipt artifact, a render‑identical self‑verifying score+parity record.

Source: llm_adapter@2026-06-11

Confidence: high

 —
Feature Low

Adds typed structured output across data tools via `structuredContent` and `outputSchema`.

Adds typed structured output across data tools via `structuredContent` and `outputSchema`.

Source: llm_adapter@2026-06-11

Confidence: high

 —
Feature Low

Changes output to quiet mode everywhere, removing emoji and using tier glyphs (♡ ○ ● ◇ ◆ ★ ✪).

Changes output to quiet mode everywhere, removing emoji and using tier glyphs (♡ ○ ● ◇ ◆ ★ ✪).

Source: llm_adapter@2026-06-11

Confidence: low

 —
Feature Low

Changes generated CLAUDE.md block to follow quiet format, matching faf‑cli export.

Changes generated CLAUDE.md block to follow quiet format, matching faf‑cli export.

Source: llm_adapter@2026-06-11

Confidence: low

 —
Bugfix Medium

Fixes `faf_trust` to work again as a self‑contained local attestation.

Fixes `faf_trust` to work again as a self‑contained local attestation.

Source: llm_adapter@2026-06-11

Confidence: high

 —
Bugfix Medium

Fixes interop tools from overwriting AGENTS.md / GEMINI.md / .cursorrules / CLAUDE.md; now injects non‑destructively with write‑guard.

Fixes interop tools from overwriting AGENTS.md / GEMINI.md / .cursorrules / CLAUDE.md; now injects non‑destructively with write‑guard.

Source: llm_adapter@2026-06-11

Confidence: low

 —
Full changelog

Claude Code-native context that just works.

Five pillars, one theme — the experience an agent can parse and a human can read, the proof a third party can verify, and the integration that earns "native":

Added

  • Native SessionStart hook (--session-refresh) — every Claude Code session opens with fresh context and a one-line heartbeat: faf: context ✪ 100% — fresh. Freshness-gated (no write, no churn when current), never breaks a session; non-faf directories stay silent.
  • faf_setup (tool #35) — the explicit hook installer. Preview first (shows the exact settings JSON + path, writes nothing); confirm: true merges non-destructively into project .claude/settings.json; remove: true takes out exactly the faf hook.
  • Determinism parity hash — faf_score/faf_trust carry an engine-agnostic parity receipt: any conformant engine reproduces it; a third party verifies sha256(projection) === parityHash. Falsifiable, not self-asserted.
  • The ✪ trust receipt — a render-identical, self-verifying score+parity artifact.
  • Typed structured output across the data tools (structuredContent + outputSchema, text retained).

Changed

  • Quiet output, everywhere, always — no emoji in tool results; tier glyphs on the quiet ladder ♡ ○ ● ◇ ◆ ★ ✪. One predictable format, no toggle.
  • The generated CLAUDE.md block is quiet too — canonical format, matching faf-cli's export.

Fixed

  • Enhanced interop — your files are enhanced, never replaced. Interop tools overwrote AGENTS.md / GEMINI.md / .cursorrules / CLAUDE.md wholesale; now a non-destructive injector owns a marked block and preserves everything you've written. A build-failing write-guard makes the old behavior impossible to reintroduce.
  • faf_trust works again — self-contained local attestation.

35 tools · 547 tests, 0 fail · IANA application/vnd.faf+yaml

FAF defines. MD instructs. AI codes.

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Wolfe-Jam/claude-faf-mcp

Get notified when new releases ship.

Sign up free

About Wolfe-Jam/claude-faf-mcp

First & only persistent project context MCP. Provides .faf (Foundational AI-context Format) Project DNA with 33+ tools, Podium scoring (0-100%), and format-driven architecture. Official Anthropic Registry. 10k+ npm downloads.

All releases →

Related context

Earlier breaking changes

  • v5.9.1 Registry namespace changes to `one.faf/*`

Beta — feedback welcome: [email protected]