agentmods.dev

issue-verify

issue-verify is a command for coding agents from assafkip/kipi-system. It costs 13 tokens per session (537 once invoked), scanned A, original, MIT.

A command that runs every required check for the active work item and records proof that they passed. The proof includes each check's result and a hash of its output.

In plain words
What is it for?
Use it to run the issue's tests or other required checks, create a verified receipt when all pass, and make the issue ready for review.
Why use it?
It ensures the recorded verification refers to the exact checks defined when the issue began, rather than to a changed version of the specification.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the kipi-dsse plugin — 6 commands shipped together

not rated 109 +1 today A scan 13 tokens original MIT
View the source file assafkip/kipi-system
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 commands/assafkip/kipi-system/issue-verify
Clone the repo
git clone --depth 1 https://github.com/assafkip/kipi-system

Or install kipi-dsse, the plugin that ships this one along with the rest of its 6 commands.

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 issue-verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/assafkip/kipi-system/issue-verify.svg)](https://agentmods.dev/commands/assafkip/kipi-system/issue-verify)
Your own site
<a href="https://agentmods.dev/commands/assafkip/kipi-system/issue-verify"><img src="https://agentmods.dev/badge/commands/assafkip/kipi-system/issue-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 537 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 $0.00013 $0.00537
Opus 5 $0.00006 $0.00269
Sonnet 5 $0.00003 $0.00107
Haiku 4.5 $0.00001 $0.00054

Measured 5d ago against content hash 0b948e550990, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-verify 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 5d 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.

plugins/kipi-dsse/commands/issue-verify.md · 39 lines

What it actually says

Autonomy contract. This step is agent-handled, not founder-gated. Verify automatically once required_checks have all exited 0. Record the verified receipt without founder confirmation. The receipt itself is the audit signal: the founder reads it after the fact, not before. Founder-gated steps are still: /issue-approve, /prd-approve, /prd-split commit, and any scope amendment mid-issue. This step is not one of them.

Verify the active DSSE issue. Execute in order:

  1. Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_runner.py" status. Confirm an issue is loaded. If issue_id is null, stop and tell the founder to run /issue-start <issue-id> first.

  2. Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_runner.py" verify.

    This ONE command is the whole step. It runs every check in the spec snapshot itself, records each check's exit code and an output hash as evidence, and writes the verified receipt only if all of them exit 0.

    Do NOT run the checks by hand first. verify runs them from the snapshot taken at /issue-start, which is the thing the receipt attests to; a check you ran yourself from the live spec can differ from that snapshot, and the receipt would then describe a run nobody made. There is no way to record this receipt without running the checks -- mark verified refuses by design (ASK-402).

  3. If verify exits 0:

    • Report: "verified receipt recorded at ."
    • Read checks from its JSON output and list them, one per line (checks_run is the count).

  4. If verify exits 2:

    • It already printed which check failed and its exit code. Report that.
    • The evidence is stored even on a red run; the receipt is withheld.
    • An empty required_checks list also exits 2. That is not a passing issue, it is a spec with nothing to attest to: tell the founder to add a check or amend the spec.
    • Stop. Do not attempt to fix silently. Tell the founder.

Do not run /codex:review here. That is /issue-review. Do not edit the spec here. That happens only in /issue-start and /issue-closeout.

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. 5d ago First seen · 39 lines · 13 tokens per session scan A 0b948e550990

Subscribe to this mod's changes

issue-verify is a command published in the GitHub repository assafkip/kipi-system (109 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 537 once invoked, about $0.0001 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 2026-08-30.

Project managementTestingagent-frameworkai-agentsai-memoryclaude-codeknowledge-managementmarkdown
Related

Other commands, from other repositories

capture

Search first: /mnemonic:search {relevantkeywords} Capture after: /mnemonic:capture {namespace} "{title}".

modeled-information-format/mnemonic · 6 tokens

recall

Recall memories with filtering and search.

modeled-information-format/mnemonic · 9 tokens

custodian

Unified memory custodian for audits, validation, and maintenance.

modeled-information-format/mnemonic · 14 tokens

integrate

Wire mnemonic memory operations into other Claude Code plugins.

modeled-information-format/mnemonic · 12 tokens

add-test

Interactively add a new test definition to the test suite.

modeled-information-format/mnemonic · 14 tokens

run-tests

Run automated functional tests using the hook-driven test framework. Execute the test suite to validate all project functionality.

modeled-information-format/mnemonic · 24 tokens