mastermind-diagnose

mastermind-diagnose is a skill for Claude Code, Codex from monoes/monomind. It costs 41 tokens per session (2,025 once invoked), scanned A, original, Apache-2.0.

A diagnostic workflow for finding where agent work stopped, repeated itself, or became too deep. It produces a proposed fix plan that must be approved before code changes.

In plain words
What is it for?
Use it to scan stalled work, investigate a particular issue or agent, and produce a diagnosis report.
Why use it?
It separates real blockers, such as missing approval or dependencies, from false stops and limits recovery loops that could continue forever.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to scan stalled work, investigate a particular issue or agent, and produce a diagnosis report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/monoes/monomind/mastermind-diagnose
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.

Any agent
npx skills add monoes/monomind --skill mastermind-diagnose
Clone the repo
git clone --depth 1 https://github.com/monoes/monomind

Made for: Claude Code, Codex.

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 mastermind-diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/monoes/monomind/mastermind-diagnose/github.svg)](https://agentmods.dev/skills/monoes/monomind/mastermind-diagnose)
Your own site
<a href="https://agentmods.dev/skills/monoes/monomind/mastermind-diagnose"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-diagnose/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 mastermind-diagnose

Your own site · 80×15
<a href="https://agentmods.dev/skills/monoes/monomind/mastermind-diagnose"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-diagnose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,025 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 $0.00041 $0.02025
Opus 5.5 $0.00016 $0.00810
Sonnet 5.5 $0.00008 $0.00405
Haiku 4.5 $0.00004 $0.00202

Measured 2d ago against content hash 8b975786266b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mastermind-diagnose 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/skills/mastermind-diagnose/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mastermind Diagnose

This skill is invoked directly via /mastermind-diagnose.


Inputs

  • brain_context: BRAIN CONTEXT block (injected by command, or loaded below if standalone)
  • org_name: org to investigate (required)
  • issue_id: specific issue or task ID that stalled (optional — omit to scan all stalled work)
  • agent_id: scope investigation to a specific agent (optional)
  • action: scan | diagnose | report
  • caller: command | master

Three Invariants (MUST be preserved in all analysis and proposed fixes)

Every diagnosis and every proposed rule must hold these three invariants together:

  1. Productive work continues. Agents with a clear next action must keep working without needing a human to wake them.
  2. Only real blockers stop work. Stops happen when something genuinely cannot proceed (missing approval, missing dependency, human owner). Pseudo-stops must be detected and routed.
  3. No infinite loops. Recovery and continuation loops must be bounded and distinguishable from genuinely productive continuation.

If a proposed fix violates any invariant, drop it or rework it. State explicitly how each invariant is held.


Step 0 — Brain Load (standalone only)

If caller is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: ops.


Step 1 — Load Org State

orgFile=".monomind/orgs/${org_name}.json"
[ ! -f "$orgFile" ] && { echo "ERROR: Org '${org_name}' not found."; exit 1; }

stateFile=".monomind/orgs/${org_name}-state.json"
activityFile=".monomind/orgs/${org_name}-activity.jsonl"
issuesFile=".monomind/orgs/${org_name}-issues.json"
routinesFile=".monomind/orgs/${org_name}-routines.json"

Step 2 — Execute Action

scan (default)

Scan for stalled work across the org:

echo "STALL SCAN — $org_name"
echo "════════════════════════════════════════════════════════"

ts=$(date -u +%Y-%m-%dT%H:%M:%SZ)
now=$(date +%s)

echo ""
echo "AGENT HEARTBEATS"
echo "────────────────────────────────────────────────────────"

python3 - "$orgFile" "$stateFile" "$now" <<'PYEOF'
import json, sys, os
from datetime import datetime, timezone

org = json.load(open(sys.argv[1]))
state_path = sys.argv[2]
now = int(sys.argv[3])

hb = {}
if os.path.exists(state_path):
    try:
        state = json.load(open(state_path))
        for r in state.get("roles", []):
            hb[r.get("id","")] = r.get("last_heartbeat")
    except:
        pass

roles = org.get("roles", [])
stalled = []
for r in roles:
    rid   = r.get("id","?")
    title = r.get("title",rid)
    last  = hb.get(rid)
    if not last:
        age = "never"
        stalled.append((rid, title, "no heartbeat"))
    else:
        try:
            dt = datetime.fromisoformat(last.replace("Z","+00:00"))
            age_s = now - int(dt.timestamp())
            age = f"{age_s//60}m ago"
            if age_s > 3600:
                stalled.append((rid, title, f"stale ({age})"))
        except:
            age = "?"
    print(f"  {rid:<28} {title:<24} last: {last or 'never'}")

print()
if stalled:
    print(f"  STALLED AGENTS ({len(stalled)}):")
    for rid, title, reason in stalled:
        print(f"    ⚠  {rid}  {title}  — {reason}")
else:
    print("  All agents have recent heartbeats.")
PYEOF

echo ""
echo "OPEN ISSUES (stall candidates)"
echo "────────────────────────────────────────────────────────"

if [ -f "$issuesFile" ]; then
  python3 - "$issuesFile" "$now" <<'PYEOF'
import json, sys
from datetime import datetime, timezone

data = json.load(open(sys.argv[1]))
now  = int(sys.argv[2])

issues = [i for i in data.get("issues",[])
          if i.get("status") in ("open","in_progress","in_review")]

if not issues:
    print("  (no open/stalled issues)")
else:
    for iss in issues[:20]:
        iid   = iss.get("id","?")[:28]
        title = iss.get("title","-")[:38]
        st    = iss.get("status","?")
        upd   = iss.get("updatedAt","-")[:10]
        asgn  = (iss.get("assigneeId") or "—")[:20]
        print(f"  [{st:<11}] {title:<38} assigned={asgn}  updated={upd}")
PYEOF
else
  echo "  (no issues file)"
fi

echo ""
echo "  For deep diagnosis: /mastermind-diagnose --org $org_name --action diagnose --issue-id <id>"

Read the full file on GitHub · 250 lines

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 · 250 lines · 41 tokens per session scan A 8b975786266b

Subscribe to this mod's changes

mastermind-diagnose is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 2,025 once invoked, about $0.0002 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 2026-10-26.

Related

Other skills, from other repositories

diag-harness

Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.

ruvnet/metaharness · 85 tokens

developing-openrig

Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a behaviour, choosing which tests to run, testing a change without disturbing the OpenRig daemon your own session runs on, judging whether a diff touches a high-risk area, or preparing a pull request. Not…

mvschwarz/openrig · 84 tokens

neuron-monitoring

Monitor Neuron AI agents and workflows with events observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, or needs to understand why an agent is behaving a certain way. Also trigger for tasks involving agent…

neuron-core/neuron-ai · 80 tokens

rest-graphql-debug

Debug REST and GraphQL APIs layer by layer: connectivity, timeouts, TLS, auth, request format, parsing and semantics, with a status-code playbook and a clean repro for every finding.

androoAGI/starnet · 45 tokens

oma-observability

Design or troubleshoot telemetry, SLOs, and incident diagnostics. Route to the relevant signal, system boundary, or vendor guide.

first-fluke/oh-my-agent · 31 tokens

upgrade-harness

Drift detection + apply for a scaffolded harness. Re-renders the template with the same vars, computes added/removed/changed file plan, and applies with Git-style conflict markers or .rej files. Default is dry-run.

ruvnet/metaharness · 51 tokens