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 mehrad-dm/mastermind --skill convergegit clone --depth 1 https://github.com/mehrad-dm/mastermindWrote 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/mehrad-dm/mastermind/converge)<a href="https://agentmods.dev/skills/mehrad-dm/mastermind/converge"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/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/mehrad-dm/mastermind/converge"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/converge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00113 | $0.01421 |
| Opus 5.5 | $0.00045 | $0.00568 |
| Sonnet 5.5 | $0.00023 | $0.00284 |
| Haiku 4.5 | $0.00011 | $0.00142 |
Grade A, and why
converge 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 15d 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MasterMind: Converge
The task list says what was meant. The code says what happened. This closes the gap: it reads the
feature's documents as the only source of intent, checks the code against every item, and appends
what is missing as new tasks for build. Layout and IDs: ~/.mastermind/engineering/core/spec-driven.md.
Feature: $ARGUMENTS.
The one write the assessment may make
The assessment appends a ## Phase N: Convergence section to tasks.md. Nothing else. It never edits
spec.md, plan.md, an existing task, a previous convergence phase, or any code. When nothing is
missing, tasks.md stays byte for byte unchanged and no empty heading is added. Closing a converged
feature, below, is a separate step taken after the verdict.
Who runs it
The session that built the feature already believes it is finished. Dispatch a fresh-context subagent with the feature folder, the constitution and repository access, and nothing about how the build went. Where no isolated context exists, run it yourself and label the result self-graded.
Method
- Require the documents.
spec.md,plan.mdandtasks.mdmust exist. If one is missing, stop and name the skill that produces it. Missing code is not a stop: see the last gotcha. - List the intent. One line per
FR-###,US#/AC#, success criterion needing build work, plan decision that names a file or behavior, constitutionMUST, and existing task. - Bound the search to the paths
plan.mdandtasks.mdname, plus a search for each requirement's key terms. Do not wander past what the documents define. Before marking anythingmissing, search again with the code's own name for the concept, starting from the brief's glossary: a gap in wording is not a gap in code. A code index, when the project has one, can suggest where to look. Evidence still comes from reading the source, and absence from an index never provesmissing. - Check every item against the code, every task included, ticked or not. A ticked box is a
claim, not evidence. Evidence is a file and line, a command's output, or a passing check from
quickstart.md. - Run it, not only read it. Run every step in
quickstart.md, then the unhappy paths the spec's edge cases name. Contradictions between two documents surface here, where reading misses them. - Classify each gap:
What ships with it
1 file 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.
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.
- 15d ago First seen · 95 lines · 113 tokens per session scan A 19487d9e8441
converge is a skill published in the GitHub repository mehrad-dm/mastermind (23 stars, last pushed 6d ago), licensed MIT. It adds 113 tokens to every session and 1,421 once invoked, about $0.0005 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 2026-10-08.
Other skills, from other repositories
code-review
Run a thorough self-review pass on the most recent change.
code-review
Use when reviewing code for bugs, security issues, performance problems, or adherence to best practices. Provides structured code review with severity levels and actionable feedback.
code-coherence-review
Reviews code and plans for logic coherence, correctness, and structural integrity.
reviewer-architect-adversarial
Adversarial plan review — structural validation and assumption attack on grill artifacts before implementation begins.
code-quality-review
Reviews code and plans against the project's coding rules.
review-loop
Two-mode review loop — single reviewer per epic, three reviewers for full branch.