harness-feedback

harness-feedback is a skill for Claude Code, Codex from andr-ca/agentharness. It costs 83 tokens per session (1,876 once invoked), scanned A, original, MIT.

A feedback process for problems encountered while using the coding-agent setup, such as failed hooks, unclear instructions, or differences between guidance and reality.

In plain words
What is it for?
Use it whenever the agent harness causes friction, including unexpected tool behaviour, violated requirements, or instructions that are difficult to apply.
Why use it?
It ensures immediate workarounds are followed by a local record and an upstream report, so recurring setup problems can be fixed.

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/andr-ca/agentharness/harness-feedback
Any agent
npx skills add andr-ca/agentharness --skill harness-feedback
Clone the repo
git clone --depth 1 https://github.com/andr-ca/agentharness

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for harness-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/andr-ca/agentharness/harness-feedback.svg)](https://agentmods.dev/skills/andr-ca/agentharness/harness-feedback)
Your own site
<a href="https://agentmods.dev/skills/andr-ca/agentharness/harness-feedback"><img src="https://agentmods.dev/badge/skills/andr-ca/agentharness/harness-feedback.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,876 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 $0.00083 $0.01876
Opus 5 $0.00042 $0.00938
Sonnet 5 $0.00017 $0.00375
Haiku 4.5 $0.00008 $0.00188

Measured 4d ago against content hash c83f706efd94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-feedback 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 4d 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.

.claude/skills/harness-feedback/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Feedback Loop

When friction is discovered during harness usage — a hook that didn't fire, guidance that was contradictory, a mandate violated in practice, or tool output diverging from documentation — capture and escalate it by default. The goal is to ensure harness improvements flow upstream without requiring users to notice and report them manually.

Procedure

1. Address the immediate problem

Work around or fix the specific friction blocking your session — do not defer this step or leave it for later. Examples:

  • A hook expected to run but didn't? Inspect core.hooksPath, check hook file permissions, run it manually if necessary.
  • Guidance was unclear? Disambiguate it by reading related docs or asking for clarification.
  • A mandate was hard to apply? Document what made it hard and propose a better framing.

2. Log it locally

Append a dated entry to docs/operational/harness-feedback.md (create it with a short header if it doesn't exist). Use this template:

## [ISO 8601 date] – [one-line summary]

**Recurrence key:** `[stable-kebab-case-slug]`

**Harness version:** [commit SHA or tag of the harness in use]

**What happened:** [The friction event and when you noticed it]

**Root cause:** [Why did this happen? What in the harness design or docs caused it?]

**Impact:** [How did it affect your session or workflow?]

**What agentharness should change:** [Concrete recommendation — a new check, clearer guidance, a new tool, a code fix, etc.]

**Corrective action taken:** [What you did to work around or fix it] Logged upstream as #[issue-number] — or "Not filed upstream (opted out via .agentharness-no-upstream-feedback)".

Optional structured fields. Add any of these when you actually have the information — none are mandatory, and a one-off entry with just the fields above is still a complete, valid entry:

**Event class:** [hook-failure | ambiguous-guidance | mandate-violation | tool-output-mismatch | other]

**Observed vs. inferred:** [Directly observed (you saw the failure happen) or Inferred (you're reasoning from symptoms without a direct repro)]

**Evidence reference:** [Link or path to the transcript, log, or command output that shows this — not the raw content, a pointer to it]

**Severity:** [blocking | degraded | cosmetic]

**Workaround:** [What let the session continue despite the friction, if anything]

**Resolution:** [Fixed upstream in #N | Still open | Won't-fix, because ...]

Read the full file on GitHub · 158 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. 4d ago First seen · 158 lines · 83 tokens per session scan A c83f706efd94

Subscribe to this mod's changes

harness-feedback is a skill published in the GitHub repository andr-ca/agentharness (1 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,876 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.

Related

Other skills, from other repositories

kami-deck

A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.

nexu-io/open-design · 49 tokens

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

fs-editorial-forest

Art-directing a fashion house's annual report — the editorial system, the photography rhythm, and the data spreads. Built as a decision-grade design craft deck for brand stakeholders, exec audience.

nexu-io/open-design · 44 tokens

html-ppt-zhangzara-stencil-tablet

A workplace-safety compliance review for a manufacturing regulator — findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership.

nexu-io/open-design · 49 tokens

simple-deck

OpenDesign's operating review: growth, burn, and the concrete path to sustainability without losing the open ethos. Built as a decision-grade corporate strategy deck for leadership team.

nexu-io/open-design · 38 tokens

html-ppt-zhangzara-coral

OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.

nexu-io/open-design · 55 tokens