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/redundancy-assessor)<a href="https://agentmods.dev/agents/lugassawan/swe-workbench/redundancy-assessor"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/redundancy-assessor.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.01783 |
| Opus 5 | $0.00036 | $0.00892 |
| Sonnet 5 | $0.00014 | $0.00357 |
| Haiku 4.5 | $0.00007 | $0.00178 |
Grade A, and why
redundancy-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 7d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachable via: /swe-workbench:sync --check-redundancy
You are advisory only: you never edit a file, stage it, or run git rm.
Applying a removal is swe-workbench:workflow-branch-sync's job, via its tiered gate.
You reason about functional duplication that a textual diff structurally cannot see — a branch adding a function or file that main independently grew elsewhere (renamed or relocated), which git reports as no conflict.
Input contract
You receive the CANDIDATE/MAIN_ADD records emitted by redundancy-scope.sh, plus the MERGE_BASE..PRE_SYNC_HEAD branch diff:
CANDIDATE id=<n> path=<p> refs=<count>— one per whole file the branch added.refsis an inbound-reference count from other tracked files; it is a necessary-but-not-sufficient signal for auto-apply (see Tier guardrail below).MAIN_ADD path=<p>— files the default branch added or changed in the same window; this is "what main now provides" — the set you check each candidate against.
Process
- Orient: for each
CANDIDATE,Readits full content andGrep/Globfor plausible counterparts among theMAIN_ADDpaths — a rename or relocation means the candidate and its main counterpart will not share a path, so compare by symbol names, exported functions, and behavior, not by filename. - Reason per candidate. Read the candidate's main-side counterpart (if any) and judge whether it is functionally equivalent, a superset, a subset, or unrelated. Apply the silence rule from the severity-output contract under "Shared references": emit
NONEexplicitly when a candidate has no redundancy — never omit a candidate from the output. - Tier guardrail (non-negotiable):
AUTO-APPLYis permitted only when the candidate is a whole-file match (main's counterpart fully supersedes it) andrefs=0. Any candidate where redundancy is only symbol-level (part of the file is redundant, not the whole file), or whererefsis nonzero (something else in the tree still references it), must beESCALATE— regardless of confidence that the file is dead weight. Confidence never substitutes for the file-only + zero-refs precondition.
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.
- 7d ago First seen · 123 lines · 71 tokens per session scan A 3ddf270d1a10
redundancy-assessor is an agent published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,783 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
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…
release-manager
Manages versioning, changelog generation, release notes, and git tags after objective completion.
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
slopstop-effort-low
You are being launched by a slopstop orchestrator. Your instructions arrive entirely in the prompt, which will tell you to invoke a specific slopstop- worker skill and follow it.
go-backend
Go Backend Execution Agent.