completion-gate

A final checker for claims that an agent has finished work, such as saying tests pass or a bug is fixed. It compares those claims with actual evidence and checks whether the result is complete, correct, and consistent with the project.

In plain words
What is it for?
Use it as a release gate to review agent reports, detect unfinished placeholder code, audit whether enough work was done, and decide whether claims are confirmed, unconfirmed, or contradicted.
Why use it?
Agents can report success without having proved it, or finish only part of a task. This checker catches unsupported, incomplete, or contradicted completion claims before a merge or commit.

Agent

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 agents/rune-kit/rune/completion-gate
Clone the repo
git clone --depth 1 https://github.com/Rune-kit/rune
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 307 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 $0.00032 $0.00307
Opus 5 $0.00016 $0.00153
Sonnet 5 $0.00006 $0.00061
Haiku 4.5 $0.00003 $0.00031

Measured 2d ago against content hash b5c0cfca2e5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

completion-gate 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 2d 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.

agents/completion-gate.md · 28 lines

What it actually says

You are the completion-gate skill — Rune's claims validator.

Quick Reference

Workflow:

  1. Extract all completion claims from agent output ("tests pass", "build succeeds", "fixed", etc.)
  2. Stub detection: scan new files for TODO/NotImplementedError/placeholder patterns
  3. Self-Validation: extract implicit claims from skill's SKILL.md
  4. Execution Loop Audit: detect observation chains (6+ reads), low effect ratio (<20%), repeating patterns
  5. Match evidence: for each claim, find tool output that proves it
  6. 3-Axis verification: Completeness (all tasks done), Correctness (tests verify real behavior), Coherence (follows patterns)
  7. Verdict: CONFIRMED / UNCONFIRMED / CONTRADICTED

Critical Rules:

  • Every claim requires evidence — no evidence = UNCONFIRMED = BLOCK
  • Default-FAIL mindset: actively seek 3-5 issues; zero issues = red flag
  • Check for partial completion (80% but claimed 100%)
  • All 3 axes (Completeness/Correctness/Coherence) must be represented

Read skills/completion-gate/SKILL.md for the full specification.

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. 2d ago First seen · 28 lines · 32 tokens per session scan A b5c0cfca2e5e

Subscribe to this mod's changes

completion-gate is an agent published in the GitHub repository Rune-kit/rune (84 stars, last pushed 16d ago), licensed MIT. It adds 32 tokens to every session and 307 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

polymath

Cross-disciplinary synthesis; spawns domain-specific subagents, synthesizes findings across domains, and produces integrated insights.

pjt222/agent-almanac · 25 tokens

insistir-reviewer

Cross-review agent for insistir multi-agent orchestration. Reviews another agent's implementation and sends structured findings to the lead. Read-only — cannot edit or write files. Can run verification commands (tests, typecheck, lint) via whitelisted Bash. Enforces quality without gatekeeping. Do NOT use directly …

JairoTorregrosa/jaiskills · 76 tokens

insistir-researcher

Research agent for insistir orchestration. Researches best practices, framework documentation, and codebase patterns. Read-only — cannot edit or write files. Do NOT use directly — spawned by insistir skill orchestration.

JairoTorregrosa/jaiskills · 50 tokens

insistir-learnings-researcher

Knowledge search agent for insistir multi-agent orchestration. Searches docs/solutions/ for past solutions relevant to a query using grep-first strategy with parallel keyword searches including synonyms. Read-only — cannot edit, write, or execute commands. Do NOT use directly — spawned by insistir skill orchestration.

JairoTorregrosa/jaiskills · 68 tokens

insistir-worker

Implementation agent for insistir multi-agent orchestration. Implements a task or applies review fixes, commits, reports to lead. Do NOT use directly — spawned by insistir skill orchestration.

JairoTorregrosa/jaiskills · 42 tokens

askit-explorer

Surveys a repository broadly and reports a structural map of its components and layout. Use when delegating broad read-only exploration - the bounded discovery role for answering what exists and how a repo is organized.

product-on-purpose/agent-skills-toolkit · 45 tokens