Agent skill

Comet Verify

by rpamis in rpamis/comet

Comet Phase 4: Verify and Close. An agent skill from rpamis/comet.

MITAuto-check passedAgent Workflows

Install Comet Verify

skills CLI
$ npx skills add rpamis/comet --skill comet-verify -a claude-code

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

GitHub CLI
$ gh skill install rpamis/comet comet-verify --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/rpamis/comet.git skills-src && mkdir -p .claude/skills && cp -r skills-src/eval/local/skills/benchmarks/039-release/comet-classic-039-verify .claude/skills/comet-verify && 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
comet-verify
GitHub stars
3.2k
Token cost
~3.4k tokens
SKILL.md length
1,599 words
Files
1
Skills in repo
52
Repo updated
First seen
Licence
MIT

At a glance

Comet Phase 4: Verify and Close. An agent skill from rpamis/comet.

  • Works in 4 steps: Scale Assessment → Artifact Context Loading (Hash On-Demand… → Finishing (Superpowers) → …
  • Agent Workflows work in your project
  • SKILL.md covers Prerequisites, Steps, Exit Conditions and Automatic Handoff to Next Phase, plus 1 more section
  • Calls git, npm and mvn

What it does

Comet Verify is an agent skill from rpamis/comet. Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.

Its SKILL.md is about 3.4k 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 Agent Workflows. The repository describes itself as: Comet: agent skill harness for turning ideas into evaluated workflows. The licence is MIT.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “/comet-verify”

Workflow steps

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

  1. Scale Assessment
  2. Artifact Context Loading (Hash On-Demand Read)
  3. Finishing (Superpowers)
  4. Record Verification Evidence

What it can do on your machine

Read from SKILL.md and the folder at commit 0fd42a0. 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:

    • git
    • npm
    • mvn
    • cargo

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

  • Network

    No URLs in SKILL.md. Its commands use git and npm, which can reach the network depending on how they are called.

    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

Comet Verify loads about 3.4k tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 1,599 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~3.4k

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 rpamis/comet at commit 0fd42a0, republished under its MIT licence (© rpamis). 1,599 words, ~3,408 tokens.

Download SKILL.mdSave it as .claude/skills/comet-verify/SKILL.md (or your agent's skills folder).
name
comet-verify
description
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.

Comet Phase 4: Verify and Close (Verify)

Prerequisites

  • Code committed (Phase 3 complete)
  • All tasks.md tasks completed

Steps

0a. Output Language Constraint

Verification reports and branch-handling notes must use the language of the user request that triggered this workflow.

0b. Entry State Verification (Entry Check)

Execute entry verification:

bash
COMET_ENV="${COMET_ENV:-$(find . "$HOME"/.*/skills "$HOME/.config" "$HOME/.gemini" -path '*/comet/scripts/comet-env.sh' -type f -print -quit 2>/dev/null)}"
if [ -z "$COMET_ENV" ]; then
  echo "ERROR: comet-env.sh not found. Ensure the comet skill is installed." >&2
  return 1
fi
. "$COMET_ENV"
"$COMET_BASH" "$COMET_STATE" check <change-name> verify

Proceed to Step 1 after verification passes. The script outputs specific failure reasons when verification fails.

Idempotency: All verify phase checks can be safely re-executed. If verify_result is already pass and branch_status is handled, verification is complete — execute guard to transition. If verify_result is pending, start verification from the beginning.

1. Scale Assessment

Execute scale assessment:

bash
"$COMET_BASH" "$COMET_STATE" scale <change-name>

The script automatically counts tasks, delta spec count, changed file count, determines light or full verification mode, and sets the verify_mode field. Decision rule (any condition triggers full): tasks > 3, delta spec capabilities > 1, changed files > 4.

Before verification begins, handle uncommitted changes through comet/reference/dirty-worktree.md protocol. Verify phase special handling:

  1. If dirty diff belongs to current change and involves implementation, tests, tasks, delta spec, or design doc changes, do not fix or commit directly in verify phase; report failures and enter Step 1b verification failure decision blocking point
  2. If dirty diff is only verify phase artifacts (e.g., verification report draft, branch handling records), may continue and record state in verify phase
  3. If dirty diff shows implementation but tasks.md not checked, treat as build state lag; report failures and enter Step 1b, let user decide to roll back for fix or accept deviation

Only after user chooses fix, allow rollback to build phase:

bash
# Execute only after user confirms fix
"$COMET_BASH" "$COMET_STATE" transition <change-name> verify-fail

Note: When verify-fail rolls back to build, branch_status is not reset. If branch handling was already completed during the first verify attempt, skip the branch handling step on re-verify and keep the existing branch_status: handled.

Note: If every task in build phase was committed, the script's file count based on working tree diff may underestimate change scale. In this case, must read plan file header base-ref and verify with commit range:

bash
PLAN=$("$COMET_BASH" "$COMET_STATE" get <change-name> plan)
BASE_REF=$(grep '^base-ref:' "$PLAN" 2>/dev/null | head -1 | sed 's/^base-ref: *//')
git diff --stat "$BASE_REF"...HEAD

If commit range shows changes exceed lightweight threshold (> 4 files, cross-module coordination, or delta spec spans more than 1 capability), manually set to full verification:

bash
"$COMET_BASH" "$COMET_STATE" set <change-name> verify_mode full

Override mechanism: If the agent or user believes the automated assessment is inappropriate, override at any time with "$COMET_BASH" "$COMET_STATE" set <change-name> verify_mode <light|full>.

1b. Verification Failure Decision (Blocking Point)

When verification does not pass, must follow the comet/reference/decision-point.md protocol to pause and wait for the user to decide whether to fix or accept the deviation. Must not automatically run "$COMET_BASH" "$COMET_STATE" transition <change-name> verify-fail, nor automatically invoke /comet-build.

When pausing, must list:

  • Failed items
  • Whether CRITICAL or IMPORTANT (build failure, test failure, security issues, core acceptance scenario failure, lightweight code review correctness/security/edge-case issue)
  • Recommended handling approach

Uncertainty principle: When severity is unclear, downgrade (SUGGESTION > WARNING > CRITICAL). Only use CRITICAL for build failures, test failures, and security issues; ambiguous or uncertain issues should be WARNING or SUGGESTION.

After user selection, continue as follows:

  • Fix all: Run "$COMET_BASH" "$COMET_STATE" transition <change-name> verify-fail, then invoke /comet-build to fix
  • Handle item by item: CRITICAL or IMPORTANT failures must be fixed; WARNING/SUGGESTION failures may choose to accept deviation, but must record acceptance reason and impact scope in verification report. If any CRITICAL or IMPORTANT failure exists, skipping fix to accept all is not allowed

Retry limit: After 3 consecutive verify-fail cycles, on the 4th failure the agent must not automatically choose to continue fixing; must use the current platform's available user input/confirmation mechanism to pause with only two options: "Accept all deviations and record" or "Continue fixing", for the user to explicitly decide.

2. Artifact Context Loading (Hash On-Demand Read)

When verification needs to read OpenSpec artifacts, first check whether they have changed since the design phase:

bash
RECORDED_HASH=$("$COMET_BASH" "$COMET_STATE" get <change-name> handoff_hash)
CURRENT_HASH=$("$COMET_BASH" "$COMET_HANDOFF" <change-name> --hash-only 2>/dev/null || echo "")
  • If RECORDED_HASH = CURRENT_HASH and both are non-empty and neither is null: OpenSpec artifacts are unchanged. tasks.md does not need to be re-read in full (use grep -c '\- \[ \]' tasks.md to confirm completion count). proposal.md, design.md, and delta specs must still be read for comparison checks.
  • If RECORDED_HASH is empty, is null, or differs from CURRENT_HASH: artifacts have changed or hash was never recorded. Read all required files in full normally.

This optimization only skips re-reading tasks.md in full. proposal.md and design.md contain the full context needed for verification checks and must not be skipped due to hash match.

Immediately execute: Use the Skill tool to load the Superpowers verification-before-completion skill. Skipping this step is prohibited.

After the skill loads, follow the verify_mode branch:

2a. Lightweight Verification (Small Changes)

Run these 6 checks:

  1. All tasks.md tasks completed [x]
  2. Changed files match tasks.md descriptions (git diff --stat / git diff --cached --stat / git diff --stat <base-ref>...HEAD compared against tasks content)
  3. Build passes (run project-specific build command, e.g., npm run build, mvn compile, cargo build, etc.)
  4. Related tests pass
  5. No obvious security issues (no hardcoded keys, no new unsafe operations)
  6. Lightweight code review passes: use the Skill tool to load the Superpowers requesting-code-review skill and request a lightweight review that checks only correctness, security, and edge cases

The lightweight code review input should be limited to this change's diff, tasks.md, and necessary test results; the review scope covers implementation correctness, security risk, and edge cases only, and does not perform spec coverage, Design Doc consistency, or drift checks. If the review finds CRITICAL or IMPORTANT issues, treat verification as failed and enter Step 1b.

Pass criteria: All 6 items OK, no CRITICAL or IMPORTANT issues.

When not passing: Report failures, enter Step 1b verification failure decision blocking point. Only after user confirms fix, execute the following command to record failure and roll back to build phase, then invoke /comet-build to fix:

bash
# Execute only after user confirms fix
"$COMET_BASH" "$COMET_STATE" transition <change-name> verify-fail

Report format: Brief table listing 6 check results + PASS/FAIL.

Skipped items (not checked in lightweight verification):

  • spec scenario coverage
  • design doc consistency deep comparison
  • code pattern consistency suggestions that do not affect correctness, security, or edge cases
  • delta spec and design doc drift detection
Show full SKILL.md (615 more words)Show less
2b. Full Verification (Large Changes)

When scale assessment result is "large":

Immediately execute: Use the Skill tool to load the openspec-verify-change skill. Skipping this step is prohibited.

After the skill loads, follow its guidance to verify. Check items:

  1. All tasks.md tasks completed ([x])
  2. Implementation matches openspec/changes/<name>/design.md high-level design decisions
  3. Implementation matches Design Doc (technical design documents under docs/superpowers/specs/)
  4. All capability spec scenarios pass
  5. proposal.md goals are satisfied
  6. No contradictions between delta spec and design doc (if Build phase had incremental spec modifications, check if design doc has corresponding records)
  7. Associated design documents under docs/superpowers/specs/ are locatable (file exists and is related to current change)

When verification does not pass: report missing items, enter Step 1b verification failure decision blocking point. Only after user confirms fix, execute the following command to record failure and roll back to build phase, then invoke /comet-build to supplement:

bash
# Execute only after user confirms fix
"$COMET_BASH" "$COMET_STATE" transition <change-name> verify-fail

Spec Drift Handling (user decision point):

  • If check item 6 finds contradictions (delta spec has content but design doc does not reflect it), must use the current platform's available user input/confirmation mechanism as a single-select question to pause and wait for the user to choose the handling method; must not select automatically. Options:
    • Option A: Append "Implementation Divergence" section to design doc recording deviation reason. Option A is a verify phase allowed artifact; after writing, must not re-trigger Step 1b dirty-worktree decision due to that design doc change
    • Option B: After user selects B, run "$COMET_BASH" "$COMET_STATE" transition <change-name> verify-fail, then invoke /comet-build; /comet-build's Spec Incremental Update rules will load the Superpowers brainstorming skill to update Design Doc + delta spec
    • Option C: Confirm deviation is acceptable, continue verification (design doc will be marked as superseded-by-main-spec during archiving)
3. Finishing (Superpowers)

Immediately execute: Use the Skill tool to load the Superpowers finishing-a-development-branch skill. Skipping this step is prohibited.

If the Superpowers finishing-a-development-branch skill is unavailable, stop the process and prompt to install or enable Superpowers skills. Do not substitute this step with normal conversation.

After the skill loads, follow its guidance to finish. Branch handling options:

  1. Merge to main branch locally
  2. Push and create PR
  3. Keep branch (handle later)
  4. Discard work

This is a user decision point. Must follow the comet/reference/decision-point.md protocol to pause and wait for the user to choose branch handling method. Must not select based on recommendations, defaults, or current branch status. Only after the user completes selection and the corresponding operation finishes, may branch_status: handled be written.

Confirmation items:

  • All tests pass
  • No hardcoded keys or security issues
4. Record Verification Evidence

Verification report must be saved to disk and recorded in .comet.yaml; after branch handling completes, state fields must also be written. Do not manually set verify_result: pass; use guard for auto-transition.

bash
mkdir -p docs/superpowers/reports
# Write verification conclusions to report file, e.g.:
# docs/superpowers/reports/YYYY-MM-DD-<change-name>-verify.md

"$COMET_BASH" "$COMET_STATE" set <change-name> verification_report docs/superpowers/reports/YYYY-MM-DD-<change-name>-verify.md
"$COMET_BASH" "$COMET_STATE" set <change-name> branch_status handled

Exit Conditions

  • Verification report passed
  • Branch handled
  • verification_report in .comet.yaml points to an existing verification report file
  • branch_status: handled in .comet.yaml
  • Phase guard: Run "$COMET_BASH" "$COMET_GUARD" <change-name> verify --apply; after all PASS, auto-transitions to phase: archive through comet-state transition verify-pass

After both verification and branch handling are complete, run guard for auto-transition:

bash
"$COMET_BASH" "$COMET_GUARD" <change-name> verify --apply

State file auto-updates to phase: archive, verify_result: pass, verified_at: YYYY-MM-DD.

Automatic Handoff to Next Phase

Follow comet/reference/auto-transition.md. Key command:

bash
"$COMET_BASH" "$COMET_STATE" next <change-name>
  • NEXT: auto → invoke the skill pointed to by SKILL to enter the next phase
  • NEXT: manual → do not invoke the next skill; prompt user to run /<SKILL> manually
  • NEXT: done → workflow is complete, no further action needed

Note: after comet-archive starts, it must first execute the final archive confirmation blocking point and wait for the user to explicitly choose "Confirm archive" before running the archive script. Must not automatically archive just because verification passed.

Context Compression Recovery

Follow comet/reference/context-recovery.md with phase set to verify.

© rpamis, 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 eval/local/skills/benchmarks/039-release/comet-classic-039-verify of rpamis/comet.

Open the folder on GitHubat commit 0fd42a0

Compare with similar skills

Comet Verify 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.

Comet Verify compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Comet Verify this skillrpamis/comet3.2k—~3.4kAutomated 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/azqr79589 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.

    795 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 rpamis/comet

All 52 skills in this repo
  • Comet

    rpamis/comet

    A skill your agent uses when 用户要启动或恢复 Comet 工作流,需要根据 active change、.comet.yaml、hotfix/tweak 意图路由到对应阶段 Skill。

    3.2k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Comet

    rpamis/comet

    Comet workflow entry. An agent skill from rpamis/comet.

    3.2k GitHub stars~686 tokensUpdated today
    Auto-check passed
  • Comet

    rpamis/comet

    Comet — OpenSpec + Superpowers dual-star development workflow.

    3.2k GitHub stars~4.4k tokensUpdated today
    Auto-check passed
  • Comet Archive

    rpamis/comet

    Archive and deliver a Classic change. An agent skill from rpamis/comet.

    3.2k GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Comet Classic

    rpamis/comet

    Comet Classic workflow entry. An agent skill from rpamis/comet.

    3.2k GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Comet Design

    rpamis/comet

    Complete the Classic technical design and obtain user confirmation.

    3.2k GitHub stars~4.3k tokensUpdated today
    Auto-check passed

Categories

Questions about Comet Verify

What does Comet Verify do?

Comet Phase 4: Verify and Close. An agent skill from rpamis/comet. Comet Verify is an agent skill from rpamis/comet. Comet Phase 4: Verify and Close.

When should I use Comet Verify?

Comet Verify fits situations like: agent Workflows work in your project.

How do I install Comet Verify in Claude Code?

Run `npx skills add rpamis/comet --skill comet-verify -a claude-code`. Or copy the skill folder (eval/local/skills/benchmarks/039-release/comet-classic-039-verify in rpamis/comet) into .claude/skills/comet-verify in your project. Claude Code loads it when a task matches its description.

How do I install Comet Verify in Codex?

Run `npx skills add rpamis/comet --skill comet-verify -a codex`. Or copy the skill folder (eval/local/skills/benchmarks/039-release/comet-classic-039-verify in rpamis/comet) into .agents/skills/comet-verify in your project. Codex loads it when a task matches its description.

Can I use Comet Verify 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 rpamis/comet --skill comet-verify -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/comet-verify, .gemini/skills/comet-verify, .github/skills/comet-verify and .opencode/skills/comet-verify in your project.

What does Comet Verify need to run?

Going by SKILL.md and its folder, Comet Verify needs the command-line tools its instructions call (git, npm, mvn and cargo).

Does Comet Verify access the network?

SKILL.md contains no URLs. Its commands use git and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Comet Verify 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 Comet Verify use?

Comet Verify 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 Comet Verify use?

About 3.4k tokens (SKILL.md is roughly 14k 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 Comet Verify?

Skills that share tags, products or a category with Comet Verify: 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 Comet Verify?

rpamis (a GitHub organization) maintains it in rpamis/comet, which has 3,166 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on October 9, 2026.

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