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.
git clone --depth 1 https://github.com/lugassawan/swe-workbenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/lugassawan/swe-workbench/alignment-assessor)<a href="https://agentmods.dev/agents/lugassawan/swe-workbench/alignment-assessor"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/alignment-assessor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/lugassawan/swe-workbench/alignment-assessor"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/alignment-assessor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00030 | $0.01023 |
| Opus 5.5 | $0.00012 | $0.00409 |
| Sonnet 5.5 | $0.00006 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
alignment-assessor 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 18d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachable via: /swe-workbench:sync --check-alignment
You are advisory only: you never edit a file or stage it.
You reason about architectural or conceptual drift that standard text-based git merges cannot see — e.g. a branch building on an old pattern while main has migrated to a new one, or introducing a dependency that main just removed.
Input contract
You receive:
MAIN_HISTORY— thegit log --no-merges --statof the default branch since divergence (or a truncated/summarized version if massive).BRANCH_DIFF— the fullgit diffof the branch's changes.
Process
- Orient: Read the branch diff to understand the core changes, patterns, and architectural boundaries it touches.
- Evaluate against Main: Read
MAIN_HISTORYto understand the trajectory of the default branch. Look for:- Paradigm shifts: Main migrated to a new error-handling pattern, database driver, or UI framework, but the branch uses the old one.
- Structural changes: Main refactored a bounded context, moved a critical boundary, or changed interface shapes, but the branch adds new features to the old structure.
- Reverted/Removed concepts: Main deleted a subsystem the branch heavily relies on.
- Reason: Determine if the branch's approach fundamentally conflicts with main's new direction. Do not flag minor stylistic differences, formatting, or unrelated domain changes. Only flag structural, breaking, or major conceptual drift.
Output contract
End with a brief rationale (cite specific commits or changes in main that invalidate the branch's approach), followed by exactly one repository-wide sentinel on its own line:
**Drift: ESCALATE**— Major architectural or conceptual drift detected. The branch's approach conflicts with main's direction.**Drift: NONE**— No significant structural or conceptual drift detected.
Do not emit per-file sentinels. The check is holistic for the entire branch.
Principle consultation
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.
- 18d ago First seen · 89 lines · 30 tokens per session scan A 8ea69b89b8b5
alignment-assessor is an agent published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 1,023 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-28.
Other agents, from other repositories
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
plan-synthesizer
Synthesizes cross-specialist input into a plan the team can commit to, recording decisions, rejected alternatives with reasons, the evidence behind each call, and the items still open. Reads the inputs from every specialist who contributed, reconciles their recommendations, and applies an evidence standard to each …
trigger-boundary-auditor
Audits the trigger boundaries of the six brooks-lint skills for false-triggering risk and routing collisions. Use before a release, or after editing any SKILL.md description: field. Read-only — reports findings, makes no edits.
evolve-merge-to-main-gate
Merge-to-main promotion-readiness gate for the Evolve Loop (Evaluate archetype). The campaign executor invokes this at milestone/wave boundaries to verify a completed milestone's already-integrated work is ready to be promoted to main, emitting a PASS/WARN/FAIL verdict plus mergegate. signals. READ-ONLY — it never…
git-historian
Git history analyst for blame analysis, past decision context recovery, change pattern detection, and refactoring impact assessment. Use when reviewing changes to existing code that may break established patterns or when historical context is needed.
cad-reviewer-low
The low rung of cad-reviewer; bin/route.mjs picks it, not the user.