ActiveLoom / reusable workflows for coding agents

Give your agents discipline.
Prove every commit.

Coding agents write code fast, but without guardrails they regress, hallucinate passing reviews, and burn tokens in loops. ActiveLoom supplies battle-tested skills, PR-first adversarial review protocols, verifiable commit ledgers, and bounded issue autonomy for Claude Code, Codex, and Gemini — synced from one upstream to your entire repository fleet.

$ npx activeloom init --harness codex,claude,gemini

✔ Claude Code ✔ OpenAI Codex ✔ Google Antigravity / Gemini ✔ Node 18+ & Python 3.9+ ✔ Apache 2.0

Native Agent Harnesses

Claude Code, Codex, and Gemini / Antigravity with zero prompt drift.

10+

Production Skills

Hardened workflows for diagnosis, planning, task packets, and review.

100%

Verifiable Commit Evidence

Cryptographic review ledgers tied directly to Git commit SHAs.

Apache 2.0

Permissive Open Source

No SaaS seat fees, no cloud lock-in. Host and distribute freely.

Live Protocol Simulator

The multi-agent workflow in action.

Click any agent, workspace, or tab to inspect live protocol evidence ↗

activeloom-session — 3 workspaces · 4 agents

protocol: converged sync: v2

Codex on ~/wt/activescribe-streaming-r2 > feat/audio-stream

❯ activeloom critique deep --pr 242

[protocol] Draft PR #242 verified. Review tier resolved: DEEP (Trigger 2: Audio mutation & encryption boundary)

[protocol] Preflight diff validation: 4 files changed, +142 lines, -18 lines.

[protocol] Executing adversarial pass across 5 deep review lanes...

✖ DEFECT DETECTED: Unencrypted database update on encrypted column

File: apps/backend/src/transcription/stream.service.ts#L142

Violation: Column `bx_raw_payload` updated directly without `e_id` encapsulation. Violates HIPAA/PHIPA encryption invariant.

✔ Posted verified defect inline to PR #242 comment thread (commit: 4d2e1b).

✔ Automated fix diff prepared using safeEncryptedUpdate() from shared package.

⠋ Awaiting second-opinion verification from Gemini... (42s elapsed)

review-ledger.json — commit-pinned cryptographic audit record VERIFIED

{
  "$schema": "https://activeloom.ca/schemas/review-ledger-v1.json",
  "commitSha": "4d2e1b89ef01a23c7b89d2140f1a94e82b7c65d3",
  "prNumber": 242,
  "reviewTier": "deep",
  "convergenceState": "CONVERGED",
  "signatures": {
    "codex-critique": {
      "timestamp": "2026-09-14T22:15:30Z",
      "status": "APPROVED_AFTER_FIX",
      "findingsResolved": 1,
      "unresolvedBlockers": 0
    },
    "gemini-second-opinion": {
      "timestamp": "2026-09-14T22:18:12Z",
      "status": "APPROVED",
      "findingsResolved": 0,
      "unresolvedBlockers": 0
    }
  },
  "invariantsVerified": [
    "encryption_eid_enforced",
    "zero_phi_telemetry",
    "strict_typescript_no_any"
  ]
}

agent-loop on ~/wt/activebill-1274

❯ activeloom agent-loop run --issue 1274

[queue] Issue #1274 allowlisted: "Fix allocator floor calculation on tiered accounts"

[worktree] Provisioned isolated worktree: ~/wt/activebill-1274 from origin/staging

[repro] Generated regression test: tests/allocator-floor.spec.ts

[code] Modified packages/core/allocator.ts — complexity checked (24 logical lines)

✔ Test suite passed: 14 assertions clean in 840ms.

✔ Atomic conventional commit created: fix(allocator): clamp floor value to zero

✔ Pushed draft PR #412. Local /critique hook completed with 0 blockers.

✔ Issue #1274 resolved autonomously. Ready for maintainer merge.

sync-engine v2 — Fleet propagation

❯ python3 scripts/sync-engine.py --consumer-dir . --config .activeloom-config.yml

[sync] Source: loomantix/activeloom@sync-v2 (commit: 986a66b)

[sync] Updating upstream-managed skills and review workflows:

→ .agents/skills/critique/SKILL.md (updated to v2.4.0)

→ .codex/REVIEW_WORKFLOW.md (synced)

→ .github/copilot-instructions.md (re-rendered with project variables)

★ Consumer-owned exceptions preserved without modification:

✔ .review/addendum.local.md (4 local security invariants protected)

✔ .codex/skills/agent-loop/agent-loop.config (local queue config preserved)

✔ Created clean propagation PR with signed commits. Zero local drift.

›

ctx: 4% (38k / 1M) esc to interrupt

Capabilities

Engineered for teams that treat agent code like production code.

ActiveLoom replaces fragile ad-hoc system prompts with structured engineering discipline, rigorous review ledgers, and deterministic fleet sync.

01 SKILLS & WORKFLOWS

Not chat prompts. Operational skills.

ActiveLoom skills encode strict operational procedures with validation checklists and deterministic outputs. From pre-code requirements grilling (grill) and deep troubleshooting (diagnosing-bugs) to task packets.

/diagnosing-bugs READY

Step 1: Reproduce defect in isolation

Step 2: Root cause analysis (no guessing)

Step 3: Smallest meaningful fix + regression test

02 MULTI-ENGINE PARITY

Claude, Codex, and Gemini in sync.

Don't maintain three divergent prompt trees. ActiveLoom authors skills once in prompts/ and renders them natively into .claude/, .codex/, and .agents/ (Gemini / Antigravity).

One upstream definition 3 native outputs

Claude Code

OpenAI Codex

Gemini / Agy

03 REVIEW PROTOCOL

Adversarial review. Proof before edit.

No rubber-stamping. Reviewers must inspect draft PR diffs and post verified findings inline to GitHub before touching any code. Automated tier gating resolves Lean (fast critical check) or Deep (exhaustive matrix).

Review Tier Gate: Deep Tier

Trigger: Encryption, Auth & Telemetry boundaries

✓ Findings posted inline before code fix

04 CRYPTOGRAPHIC LEDGERS

Verifiable proof for every commit.

A machine-readable review-ledger.json binds review evidence, passing invariants, and multi-engine signatures directly to a specific Git commit SHA. If someone amends the commit, the ledger invalidates.

review-ledger.json SHA MATCHED

Commit: 4d2e1b89ef01a23c7b89...

✓ Signed by Codex + Gemini second-opinion

05 BOUNDED AUTONOMY

Autonomous queues with guardrails.

Let agents work your GitHub backlog safely with agent-loop. Strict issue allowlists, one isolated Git worktree per issue (~/wt/*), test-driven iteration, and automatic bail-outs when blocked.

CLI Tape Demo: LIVE

06 FLEET DISTRIBUTION

Sync 50 repos without losing local rules.

ActiveLoom's sync engine propagates skills and review updates via PRs (sync-v2) while strictly protecting consumer-owned security rules in .review/addendum.local.md.

Upstream: activeloom@sync-v2 PR #6482

Syncs: Core skills, review workflows

★ Local addenda & project rules strictly preserved

Hard Boundaries

What ActiveLoom deliberately does NOT do.

Software engineering tools earn trust through explicit non-goals. We don't lock you into a cloud, hide the prompts, or replace human review.

✔ What ActiveLoom delivers

✔ Standardized engineering skills: Planning, debugging, and review workflows that any team agent can invoke.
✔ PR-first adversarial review: Verified findings posted inline to GitHub before code modifications occur.
✔ Cryptographic review ledgers: Machine-readable proof of review convergence tied directly to git commit SHAs.
✔ Upstream fleet sync: Keep 50 repositories updated via automated PRs without clobbering repo-local rules.

✖ What we deliberately avoid

✖ No proprietary agent runtime: Bring your own Claude Code, OpenAI Codex, or Gemini CLI. No vendor lock-in.
✖ No monthly SaaS seat tax: No hosted workspace fees, no credit tokens. 100% open source and self-contained.
✖ No silent auto-merges: Agents never push directly to main or merge unvetted PRs. Every change requires human review.
✖ No clobbering of local rules: Upstream prompt improvements never overwrite your repository's custom compliance invariants.

Adoption Model

From personal trial to fleet sync.

Adopt gradually. Start by running a single skill in your personal shell, then scale up to scheduled multi-repo propagation.

Tier 0

Personal Evaluation

Try a single skill in your home directory without touching any shared repository files or configurations.

$ activeloom add critique

Tier 1

Repository Setup

Scaffold harness directories (.codex/, .claude/) and shared project instructions for your team.

$ activeloom init

Recommended

Tier 2

Scheduled Sync

Automated GitHub Actions workflow proposing upstream skill improvements via pull requests using built-in GITHUB_TOKEN.

$ activeloom init --sync

Tier 3

App-Backed Fleet

Enterprise multi-repo orchestration. Scheduled updates with cryptographic GitHub App signatures and least-privilege tokens.

$ activeloom init --sync --app

Ready to evaluate?

Give your agents real discipline today.

One command to initialize your repository. Nothing about your developer workflow changes, except now your AI agents work with verifiable proof.