Agent skill

Opencode Coverage

by ItsWendell in ItsWendell/palot

Audit Palot's OpenCode 2 operation and event coverage, analyzer or baseline regressions, published contract-surface deltas, or reviewed baseline updates.

MITAuto-check passedTesting & QA

Install Opencode Coverage

skills CLI
$ npx skills add ItsWendell/palot --skill opencode-coverage -a claude-code

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

GitHub CLI
$ gh skill install ItsWendell/palot opencode-coverage --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/ItsWendell/palot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/opencode-coverage .claude/skills/opencode-coverage && 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
opencode-coverage
GitHub stars
191
Token cost
~1.3k tokens
SKILL.md length
636 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Audit Palot's OpenCode 2 operation and event coverage, analyzer or baseline regressions, published contract-surface deltas, or reviewed baseline updates.

  • Works in 7 steps: Contract: method, path, stability,… → Transport: generated Promise client,… → Production: every location in… → …
  • Testing & QA work in your project
  • SKILL.md covers Run the audit, Interpret an operation, Review new upstream work and Baseline changes, plus 1 more section
  • Calls bun

What it does

Opencode Coverage is an agent skill from ItsWendell/palot. Audit Palot's OpenCode 2 operation and event coverage, analyzer or baseline regressions, published contract-surface deltas, or reviewed baseline updates. Ordinary event-handler fixes do not need this audit. Use opencode-runtime for release selection and runtime version alignment.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA. The repository describes itself as: Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes on Linux and macOS. The licence is MIT.

When your agent uses it

  • Testing & QA work in your project

Example prompts

  • “/opencode-coverage”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Contract: method, path, stability, request fields, and Promise-client availability.
  2. Transport: generated Promise client, SSE, or a custom transport such as PTY WebSocket.
  3. Production: every location in evidence.locations whose kind is production.
  4. Breadth: compare requestFieldsObserved with inputFields; inspect responsePathsObserved. If observedRequestCoverage.complete is false…
  5. Product path: follow the adapter into Palot contracts, state, hooks, and visible behavior.
  6. Tests: separate mocks, direct unit calls, and deterministic E2E references.
  7. Failure behavior: cancellation, errors, reconnect, stale state, and cleanup.

What it can do on your machine

Read from SKILL.md and the folder at commit 6209c6e. 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:

    • bun

    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

Opencode Coverage loads about 1.3k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 636 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 ItsWendell/palot at commit 6209c6e, republished under its MIT licence (© ItsWendell). 636 words, ~1,309 tokens.

Download SKILL.mdSave it as .claude/skills/opencode-coverage/SKILL.md (or your agent's skills folder).
name
opencode-coverage
description
Audit Palot's OpenCode 2 operation and event coverage, analyzer or baseline regressions, published contract-surface deltas, or reviewed baseline updates. Ordinary event-handler fixes do not need this audit. Use opencode-runtime for release selection and runtime version alignment.

OpenCode coverage

Use the deterministic analyzer as the source of facts. Your job is to interpret its evidence, trace important gaps, and recommend work.

Match the audit to the requested scope. For a specific operation, event, or regression, inspect its diagnostics and relevant evidence rather than producing a repository-wide inventory. Loading this skill does not authorize baseline changes or runtime upgrades.

Run the audit

Start with the pinned offline check:

sh
bun run opencode:coverage:check

For published V2 changes:

sh
bun run opencode:coverage --compare beta,dev

Read the repository-root ../../../.local/opencode-coverage/report.json. Use the Markdown report only for a quick overview.

The analyzer owns:

  • The exact installed OpenAPI inventory from @opencode/protocol/client.
  • Promise-client path mapping, including experimental and custom-transport operations.
  • Oxc AST references in production, unit tests, and deterministic E2E code.
  • Request fields passed by Palot and response paths read by Palot.
  • The exact generated OpenCodeEvent union and string-literal evidence.
  • Contract and evidence regressions against repository-root ../../../apps/desktop/opencode-coverage-baseline.json.

Interpret an operation

Trace evidence in this order:

  1. Contract: method, path, stability, request fields, and Promise-client availability.
  2. Transport: generated Promise client, SSE, or a custom transport such as PTY WebSocket.
  3. Production: every location in evidence.locations whose kind is production.
  4. Breadth: compare requestFieldsObserved with inputFields; inspect responsePathsObserved. If observedRequestCoverage.complete is false, report unresolved analysis instead of treating missing fields as unused.
  5. Product path: follow the adapter into Palot contracts, state, hooks, and visible behavior.
  6. Tests: separate mocks, direct unit calls, and deterministic E2E references.
  7. Failure behavior: cancellation, errors, reconnect, stale state, and cleanup.

Assign one interpretation after tracing:

  • absent: no Palot behavior uses it.
  • transport-only: reachable through Palot's generic transport but has no product integration.
  • partial: Palot uses the operation but leaves meaningful request, response, or state behavior unused.
  • workflow: a user or automation workflow depends on it.
  • deep: the workflow handles expected fields, failures, cancellation or reconnect where applicable, and has durable tests.
  • intentional: omission is correct for Palot, such as a migration or debug endpoint without a product need.

State evidence for the label. A production reference alone does not prove workflow or deep.

Show full SKILL.md (302 more words)Show less

Review new upstream work

Treat the exact published packages as authoritative. Stable is Palot's default update target; use Beta when requested. A published npm channel is not the OpenCode repository branch of the same name. Source-only work is a watch item until a supported publish contains it. Load opencode-runtime before comparing channels or recommending an update.

Prioritize findings in this order:

  1. Breaking changes to operations Palot uses.
  2. New event variants that can corrupt or stale Palot state.
  3. New operations that replace Palot workarounds or unlock requested product behavior.
  4. Integrated operations with no direct test evidence.
  5. Intentional omissions and low-value inventory gaps.

Baseline changes

Run the audit first and inspect every issue, added, removed, or changed operation, and event. The JSON comparison includes complete current and candidate operation records. Then pass the exact contract fingerprint shown in the report:

sh
bun run opencode:coverage --update-baseline --reviewed <contract-fingerprint>

The command preserves the pre-update report under .local/opencode-coverage/review-before-update.*. Preserve manual disposition and note entries. A lost integration needs a fix or an explicit reviewed disposition, not a blind baseline update.

Output

For a focused investigation, report the relevant contract status, evidence, finding, and next step. For a full coverage audit, report:

  • Pinned contract status.
  • Latest beta and dev deltas when requested.
  • Coverage by group.
  • Experimental operations.
  • The highest-risk absent and partial integrations.
  • Weak test and event evidence.
  • Concrete next changes with file references.

Keep raw collection out of the prose. Link to the JSON report for exhaustive data.

The investigation is complete when the requested scope is accounted for, the pinned check result and relevant unresolved diagnostics are disclosed, every assigned partial or deep label cites production and product-path evidence, and each high-priority gap in scope has a concrete next step. A failing check is a finding to explain, not permission to repair unrelated integrations or reset the baseline.

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

Files

Just SKILL.md in .agents/skills/opencode-coverage of ItsWendell/palot.

Open the folder on GitHubat commit 6209c6e

Compare with similar skills

Opencode Coverage 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.

Opencode Coverage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Opencode Coverage this skillItsWendell/palot191—~1.3kAutomated safety check: PassMIT
Web Application Testinganthropics/skills180k51 repos~966Automated safety check: PassApache-2.0
Diagnosing Bugsfossasia/eventyay-interpretation1.6k31 repos~2.1kAutomated safety check: PassApache-2.0
TDDfossasia/eventyay-interpretation1.6k28 repos~1.1kAutomated safety check: PassApache-2.0
TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph11211 repos~2.4kAutomated safety check: PassNone
TDDsanity-io/sanity6.4k20 repos~1kAutomated safety check: PassMIT

Similar skills

  • Web Application Testing

    anthropics/skills

    Official

    Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.

    180k GitHub starsUsed in 51 repos~966 tokens
    Testing & QAAuto-check passed
  • Diagnosing Bugs

    fossasia/eventyay-interpretation

    Diagnosis loop for hard bugs and performance regressions. An agent skill from fossasia/eventyay-interpretation.

    1.6k GitHub starsUsed in 31 repos~2.1k tokens
    Testing & QAAuto-check passed
  • TDD

    fossasia/eventyay-interpretation

    Test-driven development. An agent skill from fossasia/eventyay-interpretation.

    1.6k GitHub starsUsed in 28 repos~1.1k tokens
    Testing & QAAuto-check passed
  • TDD Workflow

    hellangleZ/burn-in-cceverywhere-ralph

    A skill your agent uses when writing new features, fixing bugs, or refactoring code.

    112 GitHub starsUsed in 11 repos~2.4k tokens
    Testing & QAAuto-check passed
  • TDD

    sanity-io/sanity

    Official

    Test-driven development with red-green-refactor loop. An agent skill from sanity-io/sanity.

    6.4k GitHub starsUsed in 20 repos~1k tokens
    Testing & QAAuto-check passed
  • Context Driven Development

    Ibrahim-3d/orchestrator-supaconductor

    A skill your agent uses when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md…

    380 GitHub starsUsed in 8 repos~2.9k tokens
    Testing & QAAuto-check passed

More from ItsWendell/palot

All 9 skills in this repo
  • Diffs

    ItsWendell/palot

    A skill your agent uses when changing Palot code, file, or diff rendering built on @pierre/diffs, including the Changes tab, file views, CodeView, parsing, selection, annotations, workers, or Shiki…

    191 GitHub stars~841 tokensUpdated 2 days ago
    Auto-check passed
  • Trees

    ItsWendell/palot

    A skill your agent uses when changing Palot file-tree behavior built on @pierre/trees, especially the Changes tab tree, selection, search, rename, drag and drop, Git status, or theme integration.

    191 GitHub stars~540 tokensUpdated 2 days ago
    Auto-check passed
  • Shadcn

    ItsWendell/palot

    A skill your agent uses when adding, updating, composing, or debugging source components managed by shadcn; changing apps/desktop/components.json, registries, or presets; or running the shadcn CLI.

    191 GitHub stars~795 tokensUpdated 2 days ago
    Auto-check passed
  • Opencode Runtime

    ItsWendell/palot

    Check or update Palot's OpenCode CLI, client, protocol/schema and runtime contract.

    191 GitHub stars~1.7k tokensUpdated 2 days ago
    Auto-check passed
  • Test Palot Desktop

    ItsWendell/palot

    Test Palot's native Electron renderer with preload, IPC, and OpenCode integration.

    191 GitHub stars~1.9k tokensUpdated 2 days ago
    Auto-check passed
  • Palot Performance

    ItsWendell/palot

    Measure and improve Palot desktop runtime performance. An agent skill from ItsWendell/palot.

    191 GitHub stars~3.1k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Opencode Coverage

What does Opencode Coverage do?

Audit Palot's OpenCode 2 operation and event coverage, analyzer or baseline regressions, published contract-surface deltas, or reviewed baseline updates. Opencode Coverage is an agent skill from ItsWendell/palot. Audit Palot's OpenCode 2 operation and event coverage, analyzer or baseline regressions, published contract-surface deltas, or reviewed baseline updates.

When should I use Opencode Coverage?

Opencode Coverage fits situations like: testing & QA work in your project.

How do I install Opencode Coverage in Claude Code?

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

How do I install Opencode Coverage in Codex?

Run `npx skills add ItsWendell/palot --skill opencode-coverage -a codex`. Or copy the skill folder (.agents/skills/opencode-coverage in ItsWendell/palot) into .agents/skills/opencode-coverage in your project. Codex loads it when a task matches its description.

Can I use Opencode Coverage 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 ItsWendell/palot --skill opencode-coverage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/opencode-coverage, .gemini/skills/opencode-coverage, .github/skills/opencode-coverage and .opencode/skills/opencode-coverage in your project.

What does Opencode Coverage need to run?

Going by SKILL.md and its folder, Opencode Coverage needs the command-line tools its instructions call (bun).

Does Opencode Coverage 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 Opencode Coverage 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 Opencode Coverage use?

Opencode Coverage 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 Opencode Coverage use?

About 1.3k tokens (SKILL.md is roughly 5.2k 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 Opencode Coverage?

Skills that share tags, products or a category with Opencode Coverage: Web Application Testing (anthropics/skills, 180k stars), Diagnosing Bugs (fossasia/eventyay-interpretation, 1.6k stars), TDD (fossasia/eventyay-interpretation, 1.6k stars) and TDD Workflow (hellangleZ/burn-in-cceverywhere-ralph, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Opencode Coverage?

ItsWendell (a GitHub user) maintains it in ItsWendell/palot, which has 191 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 5, 2026.

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