harness-stripping

A method for testing an agent's supporting scaffolding one part at a time and removing parts that no longer help. Scaffolding includes prompts, tool wrappers, validators, retries, and other support layers.

In plain words
What is it for?
Use it to inventory harness components, connect each one to the failure it prevents, remove one component at a time, and measure the effect with evaluations.
Why use it?
It helps reveal unnecessary complexity, cost, or delay after a model improves or a harness has accumulated old workarounds.

Skill for Claude CodeCodex

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 skills/archive228/loopkit/harness-stripping
Any agent
npx skills add Archive228/loopkit --skill harness-stripping
Clone the repo
git clone --depth 1 https://github.com/Archive228/loopkit

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,051 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 $0.00028 $0.01051
Opus 5 $0.00014 $0.00526
Sonnet 5 $0.00006 $0.00210
Haiku 4.5 $0.00003 $0.00105

Measured 2d ago against content hash 7b2b2c70d340, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-stripping 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.

skills/harness-stripping/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Stripping

Every harness component was added to compensate for a specific model failure. Models improve. Components don't retire themselves. The scaffolding that saved you on Sonnet 4.5 may be dead weight — or actively harmful — on Opus 4.6. Strip it deliberately, one piece at a time, and let evals tell you what still earns its keep.

Inspired by Prithvi's March 2026 harness post on evaluator-generator separation and the general "re-test your assumptions each model bump" discipline.

When to apply

  • A model upgrade just landed and your harness was tuned for the previous generation.
  • A component's justification is "we added this because the model used to do X" — and you haven't checked whether it still does X.
  • The harness has accreted over months and nobody remembers what half the machinery is for.
  • Cost or latency is climbing and you suspect redundant belt-and-suspenders layers.

Procedure

  1. Inventory the components. List every distinct piece of scaffolding: prompt sections, tool wrappers, post-hoc validators, retry loops, evaluator personas, structured-output enforcers, sandbox rules. One row per component. Note the failure mode each was added to prevent.

  2. Rank by suspicion. Put the components most likely to be obsolete at the top: anything added before the last two model bumps, anything targeting a failure mode you haven't seen recently, anything whose original justification is now folklore.

  3. Pick a baseline eval. You need a repeatable metric before you touch anything. Reuse an existing eval set if you have one; otherwise pick 20–60 tasks representative of production work. Record baseline score, cost, and wall-clock.

  4. Strip one component. Only one. Comment it out or gate it behind a flag — don't delete yet. Re-run the eval.

  5. Compare against baseline.

    • Score within noise, cost/latency down → the component is dead weight. Delete.
    • Score drops measurably → the component still earns its complexity. Restore and note what failure mode returned.
    • Score improves → the component was actively harmful. Delete and investigate why (often: over-constraining a now-capable model).

Read the full file on GitHub · 66 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 · 66 lines · 28 tokens per session scan A 7b2b2c70d340

Subscribe to this mod's changes

harness-stripping is a skill published in the GitHub repository Archive228/loopkit (753 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,051 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 2026-08-30.