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 roadmapgit 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/roadmap)<a href="https://agentmods.dev/skills/mehrad-dm/mastermind/roadmap"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/roadmap/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/roadmap"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/roadmap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 41 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00088 | $0.01229 |
| Opus 5.5 | $0.00035 | $0.00492 |
| Sonnet 5.5 | $0.00018 | $0.00246 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
roadmap 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MasterMind: Roadmap
Long work loses its reasoning long before it loses its code. Six sessions in, the why behind a choice is gone, and the seventh session relitigates it, or silently undoes it. This is the one artifact that outlives the sessions: a decision map the project owns and appends to for the life of the work.
The file: five sections
.mastermind/MAP.md, one per project. Nothing that isn't one of these five belongs in it.
- Destination: what done looks like, in two or three lines. What every decision is measured against.
- Decisions so far: dated, one line each, each with its why. Append-only.
- Open questions: what you can state precisely and cannot answer yet.
- Not yet specified: known unknowns, deliberately unplanned.
- Out of scope: and what it would take to change that.
A decision entry, and the reversal of one, look like this:
2026-03-04 · Sessions live in Postgres, not Redis: one datastore to operate, and
nothing needed sub-millisecond reads. → specs/auth.md
2026-05-19 · REVERSES 2026-03-04: sessions move to Redis. The read path became the
p99 at 340ms once org switching landed. The original reason still held;
the traffic changed. → PR #412
Only section 2 is append-only. The other four describe the present and get rewritten freely: a resolved question leaves "Open questions" the moment it becomes a decision.
Fog of war: don't chart what you can't see
The test for "Open questions" is whether you can state the question precisely today, not whether you can answer it. "Which queue runs the nightly export?" is an open question. "How does billing work?" isn't a question yet; it's a region of fog.
Write the fog as one line naming the unknown and what will lift it: "Billing model, unspecified until the pilot returns pricing feedback." That line is the whole entry. A map carrying a plausible plan for month three reads as decided, and the next session builds against something nobody ever chose.
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 Changed · +3 lines · +88 tokens per session 449bd6d9c598
- 1mo ago First seen · 88 lines · 0 tokens per session scan A 1d6ebfa72177
roadmap is a skill published in the GitHub repository mehrad-dm/mastermind (23 stars, last pushed 6d ago), licensed MIT. It adds 88 tokens to every session and 1,229 once invoked, about $0.0004 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.
Other skills, from other repositories
agentbook-version-control
Coordinate Git and Cross-Session Memory as version control for agent work. Use when Codex needs AgentBook status, checkpoints, history, resume or handoff, provenance, isolated agent approaches, semantic comparison, or an evidence-backed game-development tuning and playtest iteration with an explicit keep or revert…
agent-memory
Long-term and session memory across sessions.
csm-continuity
Use the complete native Cross-Session Memory (CSM) runtime for continuity, memory governance, living state, beliefs, self-model, AgentBook, checkpoints, context cache, goals, work ledger, compaction, re-entry, or handoff across Codex tasks.
csm-governance
Safely deduplicate, review, merge, and archive Cross-Session Memory. Use when memory needs cleanup, dedup, merge, archive-candidate review, or recall-quality assessment.
wisdom
Primary runtime memory skill for institutional knowledge, operational facts, patterns, and decisions. Use for ALL knowledge queries including deployment, config, and infrastructure.
handoff-relay
Emit and resume cross-session handoff artifacts. Emit captures a session's mission, state, and next steps into a versioned file at explicit checkpoints; resume boots a new session from the artifact behind a continue/revise/archive decision checkpoint. Use for context handoffs between sessions, operators, or their…