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 agentmods add skills/xcrft/mastermind/mastermind-structured-report-contractnpx skills add xcrft/mastermind --skill mastermind-structured-report-contractgit 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-structured-report-contract)<a href="https://agentmods.dev/skills/xcrft/mastermind/mastermind-structured-report-contract"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-structured-report-contract.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00973 |
| Opus 5 | $0.00024 | $0.00487 |
| Sonnet 5 | $0.00010 | $0.00195 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
mastermind-structured-report-contract 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 4d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured report contract
The only canonical machine-consumed agent handoff is
<task>/executor-report.md. The Rust controller reads that file, extracts its
sentinel-wrapped YAML, validates schema v1, and uses its supported claims and
verification observations during post-flight.
A copy returned in chat is useful to humans but is not the lifecycle record. The controller does not scrape planner chat, automatically patch a spec, or re-spawn an executor. Missing or malformed file evidence fails post-flight.
Executor tail
Append this tail to the prose report in executor-report.md:
<!-- mastermind:report-begin -->
```yaml
schema_version: 1
spec: .mastermind/tasks/<NNN>-<name>/spec.md
status: complete | partial | failed
phases:
- id: plan-1
status: done # done | pending | stopped_here | skipped
files_modified:
- path/relative/to/repository
claims:
- kind: function_added
symbol: <new symbol>
file: path/to/file
signature: "<indexed signature when available>"
- kind: integration
from: <changed caller>
from_file: path/to/caller
to: <existing callee>
to_file: path/to/callee
relation: calls
defects:
- kind: <recommended label or unclassified>
phase: plan-2
details: <concrete failure evidence>
remediation_hint: <bounded next action>
verifications:
- cmd: "<command actually run>"
result: pass | fail
output_excerpt: "<short excerpt on failure>"
observed:
exit_code: 0
tests_run: 12
```
<!-- mastermind:report-end -->
phases is the schema-v1 compatibility name for execution steps. New specs may
use IDs such as plan-1; they do not need phase-shaped prose or checklists.
The machine source of truth is
schemas/executor-report-v1.schema.json plus the stricter Rust consistency
checks. Unknown fields, unsupported versions, duplicate step IDs, empty
commands, contradictory complete reports, and reports over 1 MiB fail closed.
Field rules
complete: every reported step isdone,defectsis empty, and every verification result ispass.partialorfailed: at least one concrete defect is required.files_modified: the executor's evidence, not the scope authority. The controller calculates the real changed-file set from git and compares it with the spec.claims: onlyfunction_addedandintegrationare understood by the deterministic audit. Useclaims: []for general prose outcomes.defects[].kind: a recommended routing label fromdefect-taxonomy.md, not a closed enum and not an instruction for automatic repair.verifications: record commands actually run. Do not claim an inferred or intended check.
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.
- 4d ago First seen · 119 lines · 48 tokens per session scan A 853eac8407af
mastermind-structured-report-contract is a skill published in the GitHub repository xcrft/mastermind (11 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 973 once invoked, about $0.0002 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
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
orchestrate
Tree-aware multi-agent GitHub-issue pool. Conductor manages task-tree from task-splitting-evaluation, executing depth-first per branch while parallelizing roots/orphans. Each worker agent owns its subtree lifecycle. Conductor tracks state (pending/started/in-progress/completed/halted) in GitHub +…
bonsai-ninja
Use bonsai-ninja as compiler-backed structural evidence when mapping a codebase, finding symbols, tracing behavior, inspecting dataflow, debugging across files, reviewing change impact, exporting graph facts, or running SAST.
task-splitting-evaluation
Recursive pre-implementation GitHub task splitting and evaluation flow. Use when the user wants Claude agents to evaluate unhandled tasks, skip already-processed tasks, mark easy leaves with detailed executor-ready comments, split broad tasks into GitHub subtasks, and keep recursing until every leaf is well described…
gh-task
Run a GitHub issue end-to-end in this repository using the committed isolated-worktree workflow. Use when the user invokes $gh-task, asks to run a GitHub task, or provides a GitHub issue number.
stacklit-navigator
Use stacklit.json to navigate codebases without burning tokens on file exploration.