New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Improve Harness

by hoangnb24 in hoangnb24/repository-harness

Use only when the user explicitly invokes $improve-harness. An agent skill from hoangnb24/repository-harness.

MITAuto-check passedAgent Workflows

Install Improve Harness

skills CLI
$ npx skills add hoangnb24/repository-harness --skill improve-harness -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hoangnb24/repository-harness improve-harness --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hoangnb24/repository-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/improve-harness .claude/skills/improve-harness && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
improve-harness
GitHub stars
1.2k
Token cost
~1.1k tokens
SKILL.md length
522 words
Files
2
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Use only when the user explicitly invokes $improve-harness. An agent skill from hoangnb24/repository-harness.

  • Works in 5 steps: Preserve The Baseline → Locate The Earliest Gap → State And Apply One Intervention → …
  • Explicitly invokes $improve-harness
  • SKILL.md covers Establish Authority, 1. Preserve The Baseline, 2. Locate The Earliest Gap and 3. State And Apply One…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Improve Harness is an agent skill from hoangnb24/repository-harness. Use only when the user explicitly invokes $improve-harness. Test one authorized improvement to repository guidance or capabilities against an observed baseline and a fresh rerun. Do not infer permission from ordinary work or automatically reflect after tasks.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows. The repository describes itself as: Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents. The licence is MIT.

When your agent uses it

  • Explicitly invokes $improve-harness

Example prompts

  • “/improve-harness”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Preserve The Baseline
  2. Locate The Earliest Gap
  3. State And Apply One Intervention
  4. Require A Fresh Rerun
  5. Keep, Revise, Or Remove

What it can do on your machine

Read from SKILL.md and the folder at commit 485fd40. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Improve Harness loads about 1.1k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 522 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hoangnb24/repository-harness at commit 485fd40, republished under its MIT licence (© hoangnb24). 522 words, ~1,111 tokens.

Download SKILL.mdSave it as .claude/skills/improve-harness/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
improve-harness
description
Use only when the user explicitly invokes `$improve-harness`. Test one authorized improvement to repository guidance or capabilities against an observed baseline and a fresh rerun. Do not infer permission from ordinary work or automatically reflect after tasks.

Improve Harness

Improve one bounded future-agent behavior without turning every difficult task into permanent process. Keep consumer truth with its owner and require a fresh rerun before claiming improvement.

Establish Authority

  • Read AGENTS.md, docs/WORKFLOW.md, and applicable local instructions.
  • Confirm the request authorizes changing Harness behavior. Inspection or a request to report friction does not authorize edits.
  • Record the initial repository root, revision, branch, status, and unrelated changes. Preserve all existing work.
  • Treat invocation as authority for this bounded experiment, not for changing product policy, weakening proof, adding credentials, or mutating external systems.

1. Preserve The Baseline

Use an observed task trajectory when available. Record:

  • the representative job and accepted outcome;
  • the concrete failure and evidence;
  • human steering, relay, or recovery required;
  • the worker, repository revision, relevant external state, tools, and authority; and
  • existing proof and known limitations.

Do not diagnose a worker limitation from one run. If no observed baseline exists, stop with an experiment proposal; do not manufacture one.

Copy docs/templates/harness-improvement.md to docs/plans/active/harness-improvement-<slug>.md. Reuse an existing active record for the same experiment.

2. Locate The Earliest Gap

Trace the failure upstream to the first owner that could have prevented or exposed it:

  • Context: knowledge was absent, stale, overloaded, or not retrieved.
  • Capability: discovery, invocation, interpretation, repair, or real-system verification failed.
  • Domain ownership: no canonical type, API, state machine, or source owned the invariant.
  • Authority: permission, approval, audit, or recovery was unclear.
  • Proof: checks established a proxy rather than the accepted outcome.
  • Environment: an external prerequisite was unavailable.

Assign the correction to repository-harness, the consumer repository, the external environment, or a human decision. Do not copy consumer commands or policy into a generic upstream template.

3. State And Apply One Intervention

Before editing, write:

text
If <smallest change> is added at <owner>, then a fresh agent will
<observable change> on <representative job>, because <mechanism>.
Evidence that would weaken this:
Maintenance owner and removal condition:

Make only the authorized intervention. Prefer an existing owner, a clearer route, an actionable diagnostic, a runbook fact, a type or API, or claim-matched proof over a parallel framework. Keep unknown policy unknown. Run repository-native checks that protect the changed boundary.

Show full SKILL.md (197 more words)Show less

4. Require A Fresh Rerun

Use a fresh agent session and an equivalent starting state. Hold the worker, task class, authority, tools, and relevant external conditions materially steady. Record separately whether the intervention was available, retrieved or invoked, and relevant.

If a fresh rerun is not authorized or available, leave the record active with Decision: pending fresh rerun. Report the exact next task; do not claim the Harness improved.

5. Keep, Revise, Or Remove

Compare accepted outcome, claim-matched proof, human intervention, retries, authority behavior, and maintenance cost.

  • Keep when the rerun exercised the intervention and improved the bounded job enough to justify its cost.
  • Revise when the owner is correct but the route or interface remains hard to use.
  • Remove when it adds noise, duplicates a better owner, or does not improve the job.

Record the decision, evidence, owner, and removal condition. Move the record to docs/plans/completed/ only after native validation and the fresh-rerun decision. Preserve a removed intervention's result in the completed record.

Report

Return:

  • representative job and baseline;
  • earliest gap and owner;
  • intervention and changed files;
  • native validation;
  • fresh-rerun status and comparison;
  • keep, revise, remove, or pending fresh rerun; and
  • remaining authority, risk, or follow-up.

© hoangnb24, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/improve-harness of hoangnb24/repository-harness.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 485fd40

Compare with similar skills

Improve Harness next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Improve Harness compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Improve Harness this skillhoangnb24/repository-harness1.2k—~1.1kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k10 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k35 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers297k2 repos~5.1kAutomated safety check: PassMIT
Skill CreatorAzure/azqr79689 repos~8.2kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 10 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes

  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 35 repos~1.4k tokens
    Agent WorkflowsAuto-check passed

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    297k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    796 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

More from hoangnb24/repository-harness

  • Audit Onboarding Proposal

    hoangnb24/repository-harness

    Use only when the user explicitly invokes $audit-onboarding-proposal.

    1.2k GitHub stars~4k tokensUpdated 6 days ago
    Auto-check passed

  • Onboard Repository

    hoangnb24/repository-harness

    Use only when the user explicitly invokes $onboard-repository.

    1.2k GitHub stars~6.8k tokensUpdated 6 days ago
    Auto-check: notes

  • Engineering Wisdom

    hoangnb24/repository-harness

    Use only when the user explicitly invokes $engineering-wisdom.

    1.2k GitHub stars~910 tokensUpdated 6 days ago
    Auto-check passed

  • Encode Invariant

    hoangnb24/repository-harness

    Use only when the user explicitly invokes $encode-invariant.

    1.2k GitHub stars~668 tokensUpdated 6 days ago
    Auto-check passed

Categories

Questions about Improve Harness

What does Improve Harness do?

Use only when the user explicitly invokes $improve-harness. An agent skill from hoangnb24/repository-harness. Improve Harness is an agent skill from hoangnb24/repository-harness. Use only when the user explicitly invokes $improve-harness.

When should I use Improve Harness?

Improve Harness fits situations like: explicitly invokes $improve-harness.

How do I install Improve Harness in Claude Code?

Run `npx skills add hoangnb24/repository-harness --skill improve-harness -a claude-code`. Or copy the skill folder (.agents/skills/improve-harness in hoangnb24/repository-harness) into .claude/skills/improve-harness in your project. Claude Code loads it when a task matches its description.

How do I install Improve Harness in Codex?

Run `npx skills add hoangnb24/repository-harness --skill improve-harness -a codex`. Or copy the skill folder (.agents/skills/improve-harness in hoangnb24/repository-harness) into .agents/skills/improve-harness in your project. Codex loads it when a task matches its description.

Can I use Improve Harness in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hoangnb24/repository-harness --skill improve-harness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/improve-harness, .gemini/skills/improve-harness, .github/skills/improve-harness and .opencode/skills/improve-harness in your project.

What does Improve Harness need to run?

SKILL.md names no scripts, command-line tools or credentials: Improve Harness is instructions for the agent only.

Does Improve Harness access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Improve Harness safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Improve Harness use?

Improve Harness is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Improve Harness use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Improve Harness?

Skills that share tags, products or a category with Improve Harness: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Improve Harness?

hoangnb24 (a GitHub user) maintains it in hoangnb24/repository-harness, which has 1,243 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 4, 2026.

Source: hoangnb24/repository-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.