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 xcrft/mastermind --skill mastermind-project-historygit clone --depth 1 https://github.com/xcrft/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/xcrft/mastermind/mastermind-project-history)<a href="https://agentmods.dev/skills/xcrft/mastermind/mastermind-project-history"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-project-history.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00079 | $0.01130 |
| Opus 5 | $0.00039 | $0.00565 |
| Sonnet 5 | $0.00016 | $0.00226 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
mastermind-project-history 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 today.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind Project History
Recover decision context without inventing institutional memory. Markdown
artifacts are authoritative; mmcg_history is a rebuildable retrieval index.
Sources
The history corpus admits only:
CONTEXT.md- root-level
CONTEXT-archive-*.md .mastermind/tasks/<task>/spec.md.mastermind/tasks/<task>/executor-report.md.mastermind/tasks/<task>/audit.md.mastermind/releases/<name>.md- legacy
.mastermind/tasks/<task>/release-notes.md .mastermind/tasks/_lessons.md- Markdown files, including nested directories, under
docs/adr/,docs/adrs/,docs/decisions/,adr/,adrs/, or.mastermind/decisions/(kind: architecture_decision)
Arbitrary scratch files are not history. Git history and current runtime code may contradict or supersede a record, so inspect them when the answer is load-bearing.
Workflow
- Query
mmcg_historywith the narrowest useful terms and optionalkind. - Read the returned Markdown around each relevant match. Search rank is not confidence, and co-occurrence is not causality.
- Resolve explicit status and supersession links. An accepted or active record
can constrain the plan; a proposed record remains a proposal. Follow
Supersedeslinks in both directions and inspect the replacement's status. A newer date or filename alone does not replace an accepted decision. If status is absent or records conflict, say so. A lesson with statuscandidateis an audit signal awaiting semantic review, not active guidance and not proof of a reusable root cause. - Preserve negative history: a relevant rejected alternative, failed attempt, audit defect, or gotcha must constrain the new plan unless new evidence directly addresses its failure mode.
- Verify technical claims against current code, tests, or runtime evidence. Provenance answers "where did this claim come from?"; it does not answer "is this claim true?" User approval proves authorization, not correctness.
- If evidence is thin for a security, runtime-boundary, migration, money,
idempotency, or compatibility conclusion, return
insufficient evidenceand name the missing proof.
What ships with it
3 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.
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.
- today Changed · +29 lines · +12 tokens per session 5caa8f746ba0
- 8d ago First seen · 90 lines · 67 tokens per session scan A 8468497fb5fe
mastermind-project-history is a skill published in the GitHub repository xcrft/mastermind (11 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,130 once invoked, about $0.0004 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.
Other skills, from other repositories
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
obsidian-memory
Cross-project long-term memory over an Obsidian brain vault: recall relevant notes before a task, and persist distilled conclusions (decisions, pitfalls, solutions, progress) back after a task. The vault is an optional aggregation/projection layer — repo-local artifacts stay the per-project source of truth, and sync…
repo-harness-product
Canonical rule owner for PRD drafting, Sprint planning/execution, and native Goal-session preparation from repo-harness planning artifacts.
handoff
Use when work is changing sessions, agents, or machines and the next pass needs a compact handoff document with current state, open questions, and next steps instead of raw chat history.
project-context
Resume, handoff, and long-running repo work by keeping durable context across threads or agents: task briefs, logs, and reusable reference notes.