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.
npx skills add JKHeadley/instar --skill spec-convergegit clone --depth 1 https://github.com/JKHeadley/instarWrote 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.
[](https://agentmods.dev/skills/jkheadley/instar/spec-converge)<a href="https://agentmods.dev/skills/jkheadley/instar/spec-converge"><img src="https://agentmods.dev/badge/skills/jkheadley/instar/spec-converge/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.
<a href="https://agentmods.dev/skills/jkheadley/instar/spec-converge"><img src="https://agentmods.dev/badge/skills/jkheadley/instar/spec-converge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 94 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high Memory Poisoning · line 96 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Data Exfiltration · line 71 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 340 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00135 | $0.11126 |
| Opus 5.5 | $0.00054 | $0.04450 |
| Sonnet 5.5 | $0.00027 | $0.02225 |
| Haiku 4.5 | $0.00014 | $0.01113 |
Grade A, and why
spec-converge scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -m 90 -X POST -H "Authorization: Bearer ${AUTH:-$INSTAR_AUTH_TOKEN}" -H 'Content-Type: application/json' \ How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec-converge
Audience: the instar-developing agent. End users do not invoke this. Throughout this document, "the agent" refers to the instar-developing agent running the skill.
What this skill does
Takes a spec file, runs multiple parallel reviewers against it, updates the spec to address their findings, runs another round, and repeats until convergence. Produces a final converged spec and a comprehensive human-readable report.
The purpose is to catch architectural, security, adversarial, scalability, and integration issues BEFORE code is written, not after. The single-reviewer pattern used by /instar-dev's existing second-pass step has proven too narrow in practice — a four-reviewer parallel audit on the integrated-being ledger PR surfaced 14 serious issues that a single reviewer had missed. This skill bakes that multi-angle pattern in as the structural default for any substantive instar-dev work.
When it runs
Before /instar-dev touches any instar source, the change's spec must pass through this skill. /instar-dev's pre-commit hook refuses work unless:
- The spec file has a
review-convergence: <timestamp>entry in its frontmatter, written by this skill on successful convergence. - The spec file has an
approved: trueentry in its frontmatter, written by the user after reading the convergence report.
Both tags must be present. Without them, /instar-dev is blocked.
Input
One argument: the path to the spec file, relative to the instar repo root.
The spec file is a markdown document with YAML frontmatter. Minimum required structure:
---
title: "Short title"
slug: "url-friendly-slug"
author: "agent name"
---
# Title
## Problem statement
[what is being built and why]
## Proposed design
[how it works, at enough detail to review]
## Decision points touched
[any block/allow/route gates the design introduces, removes, or modifies]
## Open questions
[things that need human input]
The skill adds review-convergence, review-iterations, review-completed-at, and (if provided) approved fields to the frontmatter on successful convergence.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/cross-model-review.mjs 23 KB runs code
- scripts/publish-spec-review.mjs 9.1 KB runs code
- scripts/write-convergence-tag.mjs 19 KB runs code
- templates/report.md 2.9 KB
- templates/reviewer-adversarial.md 3.2 KB
- templates/reviewer-cross-model.md 3.4 KB
- templates/reviewer-decision-completeness.md 5.3 KB
- templates/reviewer-integration.md 6.8 KB
- templates/reviewer-lessons-aware.md 9.3 KB
- templates/reviewer-scalability.md 2.7 KB
- templates/reviewer-security.md 3.4 KB
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.
- 12d ago Changed · +13 lines 09aaf442a2c8
- 2mo ago First seen · 364 lines · 135 tokens per session scan A e0e1129ade0f
spec-converge is a skill published in the GitHub repository JKHeadley/instar (86 stars, last pushed today), licensed MIT. It adds 135 tokens to every session and 11,126 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
phaser-pixi-2d-games
Use when building a 2D web game with Phaser (3.x/4.x) or PixiJS 8 in TypeScript - framework vs renderer, Phaser scenes/game objects/arcade physics/groups as pools/scale manager/loader, scene shutdown cleanup, PixiJS 8 async init, Assets bundles, ticker units and destroy, and keeping rules in plain TS modules.
node-typescript-security-pitfalls
Use when reviewing Node.js or TypeScript server code - Express/Fastify/Nest handlers, Next.js server actions and route handlers, childprocess, ORM raw queries, prototype pollution, template engines, JWT and outbound HTTP clients.
node-typescript-service
Use when building or extending a TypeScript service on Node.js - Fastify, NestJS, Express or Hono, runtime validation at the boundary, strict types, the repository's ORM and migrations, async error handling, graceful shutdown.
react-typescript-patterns
Use when writing React + TypeScript components - functional components, explicit typed props, derived state over effects, and no any/unsafe casts.
V3 CLI Modernization
CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.
V3 Core Implementation
Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.