Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
Improve Kandev's AI harness from session learnings or explicit requests.
Install Harness Improvement
$ npx skills add kdlbs/kandev --skill harness-improvement -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kdlbs/kandev harness-improvement --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/kdlbs/kandev.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/harness-improvement .claude/skills/harness-improvement && rm -rf skills-srcUse ~/.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/
Install the "harness-improvement" agent skill from https://github.com/kdlbs/kandev/tree/main/.agents/skills/harness-improvement into .claude/skills/harness-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-improvement", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/kdlbs/kandev/tree/main/.agents/skills/harness-improvementType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add kdlbs/kandev --skill harness-improvement -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kdlbs/kandev harness-improvement --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kdlbs/kandev.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/harness-improvement .agents/skills/harness-improvement && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "harness-improvement" agent skill from https://github.com/kdlbs/kandev/tree/main/.agents/skills/harness-improvement into .agents/skills/harness-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-improvement", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kdlbs/kandev --skill harness-improvement -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kdlbs/kandev harness-improvement --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kdlbs/kandev.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/harness-improvement .cursor/skills/harness-improvement && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "harness-improvement" agent skill from https://github.com/kdlbs/kandev/tree/main/.agents/skills/harness-improvement into .cursor/skills/harness-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-improvement", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/kdlbs/kandev.git --path .agents/skills/harness-improvement--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add kdlbs/kandev --skill harness-improvement -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kdlbs/kandev harness-improvement --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kdlbs/kandev.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/harness-improvement .gemini/skills/harness-improvement && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "harness-improvement" agent skill from https://github.com/kdlbs/kandev/tree/main/.agents/skills/harness-improvement into .gemini/skills/harness-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-improvement", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install kdlbs/kandev harness-improvementInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add kdlbs/kandev --skill harness-improvement -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kdlbs/kandev.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/harness-improvement .github/skills/harness-improvement && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "harness-improvement" agent skill from https://github.com/kdlbs/kandev/tree/main/.agents/skills/harness-improvement into .github/skills/harness-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-improvement", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kdlbs/kandev --skill harness-improvement -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kdlbs/kandev harness-improvement --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kdlbs/kandev.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/harness-improvement .opencode/skills/harness-improvement && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "harness-improvement" agent skill from https://github.com/kdlbs/kandev/tree/main/.agents/skills/harness-improvement into .opencode/skills/harness-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-improvement", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
harness-improvement- GitHub stars
- 912
- Token cost
- ~1.3k tokens
- SKILL.md length
- 643 words
- Files
- 10 (incl. references)
- Skills in repo
- 45
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Improve Kandev's AI harness from session learnings or explicit requests.
- Works in 6 steps: Inventory first → Normalize the learning → Pick the narrowest home → …
- The user asks to record learnings
- SKILL.md covers Planner Entry, Choose The Artifact, Workflow and Guardrails
- Calls rg
What it does
Harness Improvement is an agent skill from kdlbs/kandev. Improve Kandev's AI harness from session learnings or explicit requests. Use when the user asks to record learnings, update or create skills, agents, subagents, commands, AGENTS.md/CLAUDE.md guidance, or adapt harness files across Claude, Codex, Cursor, or OpenCode.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including reference files (for example `references/agents.md`, `references/instructions.md` and `references/platforms/claude.md`).
It sits in Agent Workflows, covering Agent instruction files and Subagents. The repository describes itself as: AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry. The licence is AGPL-3.0.
When your agent uses it
- The user asks to record learnings
- AGENTS.md/CLAUDE.md guidance
- Adapt harness files across Claude
Example prompts
- “/harness-improvement”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Inventory first
- Normalize the learning
- Pick the narrowest home
- Preserve progressive disclosure
- Edit and validate
- Report
What it can do on your machine
Read from SKILL.md and the folder at commit 53a00c2. 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
Shell commands in SKILL.md call:
rg
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
Harness Improvement loads about 1.3k tokens when it runs, and up to ~7.2k if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 643 words of instructions outside code blocks.
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 kdlbs/kandev at commit 53a00c2, republished under its AGPL-3.0 licence (© kdlbs). 643 words, ~1,339 tokens.
Download SKILL.mdSave it as
.claude/skills/harness-improvement/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.- name
- harness-improvement
- description
- Improve Kandev's AI harness from session learnings or explicit requests. Use when the user asks to record learnings, update or create skills, agents, subagents, commands, AGENTS.md/CLAUDE.md guidance, or adapt harness files across Claude, Codex, Cursor, or OpenCode.
Harness Improvement
Use this skill to turn lessons from real agent sessions into durable harness changes: skills, agents, subagents, commands, scripts, and always-on instruction files.
For an explicitly requested session retrospective, use
/retro to filter lessons and propose shared-file edits.
Planner Entry
The planner may inventory, edit, and validate a small localized harness change directly. Delegate broad cross-platform migration or independent work when it has positive ROI. Do not use Kandev MCP task/session APIs for workers.
Choose The Artifact
Before editing, classify the requested improvement:
- Session learning: recurring failure, workaround, or convention discovered during a session. Read
references/session-learnings.md. - Skill: task-specific playbook loaded on demand. Read
references/skills.md. - Custom agent: an exception that requires the user to explicitly reverse the
repository's single-session policy. Read
references/agents.mdbefore acting. - Command: explicitly invoked workflow shortcut. Prefer a skill unless the user wants manual invocation only.
- AGENTS.md / CLAUDE.md / rules: always-on or path-scoped instruction. Read
references/instructions.md. - Cross-platform migration: preserving behavior across Claude, Codex, Cursor, and OpenCode. Read the relevant platform files in
references/platforms/.
If the user names a target platform for a skill, command, or instruction file, load only that platform reference. Do not create a custom agent or platform mirror unless the user explicitly requests a policy reversal.
Workflow
Inventory first
- Use
rg --filesto find existing.agents/skills,.claude,.codex,.cursor,.opencode,AGENTS.md, andCLAUDE.mdfiles. - For platform-specific formats, read the bundled files under
references/platforms/before consulting external docs. Treat those files as the first source of truth for Claude, Codex, Cursor, and OpenCode harness layout. - Check for duplicate or superseded skills/agents before adding new ones.
- Prefer updating the existing artifact when the behavior belongs to an existing workflow.
- Use
Normalize the learning
- Convert anecdotes into reusable guidance: trigger, problem, correct action, fallback, verification.
- Remove session-specific IDs, PR numbers, or temporary paths unless they are part of an example that teaches the pattern.
- Keep wording direct and operational.
Pick the narrowest home
Put durable repo-wide constraints in
AGENTS.mdor scopedAGENTS.md.Put task workflows in
.agents/skills/<name>/SKILL.md.Put deterministic logic in
scripts/when agents keep retyping fragile shell/API sequences.Avoid creating multiple aliases for the same behavior.
Separate independent policy changes: Keep factual instruction updates and CI changes required by a feature in that feature's PR. Use a separate initiative for independent workflow-policy changes unless the user requests a combined PR. Classify changes by purpose, not path.
Preserve progressive disclosure
- Keep
SKILL.mdconcise. - Move platform tables, long examples, templates, and edge-case notes to
references/. - Reference each supporting file explicitly from the main skill so future agents know when to load it.
- Review word and byte counts as well as line counts. Do not join paragraphs to satisfy a line limit. Move specialized procedures into references with explicit loading conditions. Keep each rule in one authoritative location.
- Keep
Edit and validate
- Use
apply_patchfor file edits. - Validate markdown/frontmatter shape with targeted checks:
bash git diff --check -- <changed-files> rg -n "old-skill|old-agent|stale-command" .agents AGENTS.md CLAUDE.md - Load
references/validation.mdfor the shared harness test, lint, whitespace, line-budget, and pre-commit commands. - For executable script changes, run syntax checks and a focused dry run or mocked command when possible.
- Use
Report
- Name each artifact changed.
- State why the instruction belongs there.
- Mention validation run and any bundled platform references consulted.
Show full SKILL.md (104 more words)Show less
Guardrails
- Do not blindly copy upstream examples. Adapt model names, package managers, commands, paths, and verification steps to Kandev.
- Do not add always-on instructions for rare workflows; use skills or commands.
- Keep the single-session model policy intact unless the user explicitly asks to change it and accepts the cost/context trade-off.
- Do not keep deprecated/replaced skills around without a clear compatibility reason.
- Do not web-search platform formats by default. Use external docs only when the bundled reference is missing the needed detail, conflicts with files already in the repo, or the user explicitly asks for latest/current upstream behavior; if that happens, say why before browsing.
© kdlbs, AGPL-3.0. 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 9 other files (references) in .agents/skills/harness-improvement of kdlbs/kandev.
- SKILL.md
- references/agents.md
- references/instructions.md
- references/platforms/claude.md
- references/platforms/codex.md
- references/platforms/cursor.md
- references/platforms/opencode.md
- references/session-learnings.md
- references/skills.md
- references/validation.md
Open the folder on GitHubat commit 53a00c2
Compare with similar skills
Harness Improvement 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Harness Improvement this skillkdlbs/kandev | 912 | — | ~1.3k | Automated safety check: Pass | AGPL-3.0 | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~11k | Automated safety check: Pass | CC-BY-4.0 | |
| Harness Agent Team Designerrevfactory/harness | 9.1k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| Repo Task Proof LoopDenisSergeevitch/repo-task-proof-loop | 730 | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | |
| Rules Distillationaffaan-m/ECC | 276k | 2 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Claude Docs Consultantcentminmod/my-claude-code-setup | 2.7k | — | ~959 | Automated safety check: Pass | MIT |
Similar skills
Harness Agent Team Designer
revfactory/harness
Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.
Repo Task Proof Loop
DenisSergeevitch/repo-task-proof-loop
Repo-local workflow skill for large coding tasks. An agent skill from DenisSergeevitch/repo-task-proof-loop.
Rules Distillation
affaan-m/ECC
Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.
Claude Docs Consultant
centminmod/my-claude-code-setup
Consult official Claude Code documentation from code.claude.com using selective fetching.
Creating Claude Code Agents
pr-pm/prpm
Reference for writing Claude Code agent files: location, frontmatter fields, validation limits, tool and model choices, and the required content format.
More from kdlbs/kandev
All 45 skills in this repoPR Walkthrough
kdlbs/kandev
Generate a single-file HTML walkthrough that explains a PR's purpose, user impact, interface changes, compatibility risks, and implementation.
Debug
kdlbs/kandev
Diagnose Kandev bugs, running-instance issues, UI/browser failures, and runtime behavior.
Diagram Design
kdlbs/kandev
Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel…
TDD
kdlbs/kandev
Implement changes using Test-Driven Development (Red-Green-Refactor).
Verify
kdlbs/kandev
Run a broad local verification audit only when the user explicitly requests it or PR/CI remediation requires it.
Acp Debug
kdlbs/kandev
Debug an ACP agent CLI by spawning it, speaking raw JSON-RPC, and capturing every frame to a JSONL file.
Related
Categories
Questions about Harness Improvement
What does Harness Improvement do?
Improve Kandev's AI harness from session learnings or explicit requests. Harness Improvement is an agent skill from kdlbs/kandev. Improve Kandev's AI harness from session learnings or explicit requests.
When should I use Harness Improvement?
Harness Improvement fits situations like: the user asks to record learnings; AGENTS.md/CLAUDE.md guidance; adapt harness files across Claude.
How do I install Harness Improvement in Claude Code?
Run `npx skills add kdlbs/kandev --skill harness-improvement -a claude-code`. Or copy the skill folder (.agents/skills/harness-improvement in kdlbs/kandev) into .claude/skills/harness-improvement in your project. Claude Code loads it when a task matches its description.
How do I install Harness Improvement in Codex?
Run `npx skills add kdlbs/kandev --skill harness-improvement -a codex`. Or copy the skill folder (.agents/skills/harness-improvement in kdlbs/kandev) into .agents/skills/harness-improvement in your project. Codex loads it when a task matches its description.
Can I use Harness Improvement 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 kdlbs/kandev --skill harness-improvement -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harness-improvement, .gemini/skills/harness-improvement, .github/skills/harness-improvement and .opencode/skills/harness-improvement in your project.
What does Harness Improvement need to run?
Going by SKILL.md and its folder, Harness Improvement needs the command-line tools its instructions call (rg).
Does Harness Improvement 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 Harness Improvement 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 Harness Improvement use?
Harness Improvement is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Harness Improvement use?
About 1.3k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.9k tokens, read only when the agent opens those files.
What are the alternatives to Harness Improvement?
Skills that share tags, products or a category with Harness Improvement: Task Observer (rebelytics/one-skill-to-rule-them-all, 3.2k stars), Harness Agent Team Designer (revfactory/harness, 9.1k stars), Repo Task Proof Loop (DenisSergeevitch/repo-task-proof-loop, 730 stars) and Rules Distillation (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Harness Improvement?
kdlbs (a GitHub organization) maintains it in kdlbs/kandev, which has 912 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on October 10, 2026.
Source: kdlbs/kandev on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.