agentmods.dev

issue-approve

issue-approve is a command for Claude Code from assafkip/kipi-system. It costs 14 tokens per session (592 once invoked), scanned A, original, MIT.

A command that approves a planned work item and moves it from open to in progress. It checks whether the plan stays within the previously authorized files and checks.

In plain words
What is it for?
Use it to approve the first work item through the advisor, approve later matching items automatically, or stop for founder input when the plan changes.
Why use it?
It prevents work from starting without the right approval or from quietly expanding beyond the agreed scope.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

not rated 131repo +3 today A scan 14 tokens original MIT

Good fit Use it to approve the first work item through the advisor, approve later matching items automatically, or stop for founder input when the plan changes.

Compare 6 commands from other repositories ↓
View source ↗ assafkip/kipi-system
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add assafkip/kipi-system
Claude Code
/plugin install kipi-dsse

Made for: Claude Code.

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-approve

README.md
[![agentmods](https://agentmods.dev/badge/commands/assafkip/kipi-system/issue-approve/github.svg)](https://agentmods.dev/commands/assafkip/kipi-system/issue-approve)
Your own site
<a href="https://agentmods.dev/commands/assafkip/kipi-system/issue-approve"><img src="https://agentmods.dev/badge/commands/assafkip/kipi-system/issue-approve/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for issue-approve

Your own site · 80×15
<a href="https://agentmods.dev/commands/assafkip/kipi-system/issue-approve"><img src="https://agentmods.dev/badge/commands/assafkip/kipi-system/issue-approve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 592 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00014 $0.00592
Opus 5.5 $0.00006 $0.00237
Sonnet 5.5 $0.00003 $0.00118
Haiku 4.5 $0.00001 $0.00059

Measured 2mo ago against content hash caba96ffdbfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

issue-approve 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 2mo 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-approve.md · 30 lines

What it actually says

Autonomy contract (advisor-approved, founder gated only at charter level). In the v2 rewrite topology, plan approvals route to the advisor (main session), not to the founder. Founder approval at /prd-split commit already authorized the manifest, including each issue's allowed_files and required_checks. Plan approvals refine that authorization at the issue level and are advisor-owned.

  • Issue 1 of a PRD: advisor-gated. The advisor (main session) sees the plan via the channel, replies approve (or surfaces a redirect). Founder is NOT routed unless the plan introduces a scope amendment relative to the manifest.
  • Issues 2..N of the same PRD: agent self-approves IF the loaded plan's allowed_files and required_checks match the PRD manifest verbatim AND the plan does not introduce a scope amendment. Run /issue-approve directly without waiting for advisor or founder.
  • Any deviation from the manifest (new path, removed check, mid-issue scope amendment): founder-gated. Surface the diff with [FOUNDER-INPUT-NEEDED] and wait. Scope amendments are charter-level changes the founder owns.

Founder-gated steps remain (charter-level only):

  • /prd-approve (founder owns the PRD contract)
  • /prd-split commit (founder owns the issues manifest)
  • Mid-issue scope amendments (founder owns scope)

Everything else self-progresses or routes to the advisor. Codex finding triage and disposition during /issue-closeout are agent-handled per the closeout autonomy contract.

Approve the active DSSE issue after the advisor (or, for scope amendments, the founder) has signed off on the plan. Execute in order:

  1. Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/issue_runner.py" approve. This reads the active issue spec, confirms its status is currently open, and flips it to in-progress. The command writes the spec directly — do not use the Edit tool for this.

  2. If approve exits non-zero:

    • No active issue: tell the founder to run /issue-start <issue-id> first.
    • Status already in-progress: safe to proceed, the runner is idempotent on re-approval.
    • Any other error: report it verbatim. Do not edit the spec manually to work around it.

  3. Confirm in one line: "Issue $ISSUE_ID is now in-progress. Stop-time gate is armed."

After approval, proceed with the first concrete change from the plan. All edits must target allowed_files. Normal DSSE flow resumes: /issue-verify, /issue-review, /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. 2mo ago First seen · 30 lines · 14 tokens per session scan A caba96ffdbfc

Subscribe to this mod's changes

issue-approve is a command published in the GitHub repository assafkip/kipi-system (131 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 592 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude CodeProject managementagent-frameworkai-agentsai-memoryknowledge-managementmarkdown
Related

issue-approve compared with commands from other repositories

issue-approve next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
issue-approveassafkip/kipi-systemCommand131todayMITA14Claude Code
recallmodeled-information-format/mnemonicCommand2311d agoMITA9Claude Code
querymodeled-information-format/mnemonicCommand2311d agoMITA9Claude Code
searchmodeled-information-format/mnemonicCommand2311d agoMITA8Claude Code
gcmodeled-information-format/mnemonicCommand2311d agoMITB7Claude Code
setupmodeled-information-format/mnemonicCommand2311d agoMITB8Claude Code
statusmodeled-information-format/mnemonicCommand2311d agoMITB8Claude Code