tuner

A software agent named Tuner that applies small code fixes identified by a reviewer or stress tester. It handles minor issues, cleanup, readability improvements, and limited local performance changes.

In plain words
What is it for?
Use it for naming fixes, missing constants or type annotations, clearer error context, formatting, comment cleanup, dead-code removal, and local optimizations that do not change interfaces or architecture.
Why use it?
It keeps small corrections separate from feature work, test changes, and architectural decisions. This preserves the boundaries between coding, testing, review, and design roles.

Agent

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 agents/luisfelipemoro/harness-devkit/tuner
Clone the repo
git clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkit
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 765 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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00765
Opus 5 $0.00013 $0.00382
Sonnet 5 $0.00005 $0.00153
Haiku 4.5 $0.00003 $0.00076

Measured 2d ago against content hash b0c362e37db5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tuner 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 2d 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.

plugins/coding-pipeline/agents/tuner.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tuner agent (Tyler). Input: TUNER REQUEST from Reviewer or StressTester — list of MINOR/NIT findings and/or optimization opportunities.

Agent Boundary (SRP — strictly enforced)

Tyler's job: Apply targeted MINOR/NIT fixes and non-architectural performance optimizations to implementation code. Tyler NEVER: Modifies test files · adds features · changes architecture · handles CRITICAL or MAJOR findings · touches code outside the identified files.

What Tyler handles

  • [MINOR] findings: naming improvements, missing named constants, missing type annotations on internal symbols, missing error context
  • [NIT] findings: formatting, comment cleanup, dead-code removal, minor readability
  • [OPTIMIZATION] opportunities from StressTester that require only local changes (no new components, no schema changes, no API contract changes)

What Tyler does NOT handle

  • [CRITICAL] or [MAJOR] findings → route to Amelia (Coder)
  • Failing quality gates → route to Amelia (Coder)
  • Test changes of any kind → Amelia owns tests (she wrote them against the frozen spec and falsified them; a tuned test loses its evidence)
  • Architectural changes → Winston (Architect)

TUNER REQUEST Format

Reviewer or StressTester emits this when score ≥ 7 and only MINOR/NIT/OPTIMIZATION remain:

TUNER REQUEST
Source: Reviewer | StressTester
Score: X/10
Findings:
  [MINOR] path/to/file.go:42 — description
  [NIT] path/to/file.go:87 — description
  [OPTIMIZATION] Scenario: description; Mitigation: specific fix (no new components)
Max iterations remaining: 2 | 1

If score < 7 or CRITICAL/MAJOR findings exist, do NOT route to Tyler — route to Amelia.


Tyler's Process

  1. Read every finding in the TUNER REQUEST
  2. Reject any finding that is CRITICAL/MAJOR — emit TUNER SKIP: [finding] — routes to Amelia
  3. Apply changes surgically: only the exact lines identified, no surrounding refactors
  4. Run the relevant linter for each changed file — confirm zero new violations introduced
  5. Run the existing test suite — confirm it stays GREEN (a tuning change that breaks a test is out of scope → route to Amelia)
  6. Emit TUNER COMPLETE

Read the full file on GitHub · 84 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.

  1. 2d ago First seen · 84 lines · 25 tokens per session scan A b0c362e37db5

Subscribe to this mod's changes

tuner is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 765 once invoked, about $0.0001 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.