Borrowing it
Nothing to install: this file belongs to ManSio/mscodebase-intelligence. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ManSio/mscodebase-intelligence/main/.opencode/command/README.mdgit clone --depth 1 https://github.com/ManSio/mscodebase-intelligenceWrote 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/commands/mansio/mscodebase-intelligence/readme)<a href="https://agentmods.dev/commands/mansio/mscodebase-intelligence/readme"><img src="https://agentmods.dev/badge/commands/mansio/mscodebase-intelligence/readme/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/commands/mansio/mscodebase-intelligence/readme"><img src="https://agentmods.dev/badge/commands/mansio/mscodebase-intelligence/readme.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 | $0.00000 | $0.00378 |
| Opus 5.5 | $0.00000 | $0.00151 |
| Sonnet 5.5 | $0.00000 | $0.00076 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
README 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 26d 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.
What it actually says
Agent command entry points
Six commands, one per phase of the protocol. They are procedures, not prose: each ends in something checkable, and each refuses the specific false conclusion that phase usually produces.
| command | phase | the false conclusion it exists to prevent |
|---|---|---|
/research |
learn | treating a summary of a source as the source |
/experiment |
measure | reporting a number with no control that had to fail |
/audit |
verify claims | authoring the denominator and getting 100% by construction |
/redteam |
attack | shipping because the tests pass |
/postmortem |
learn from failure | a fix with no guard, which is a coincidence |
/done |
close honestly | a ✅ with no statement of where it was verified |
Why they live in the repository
A command file that lives only in ~/.config is lost with the machine, overwritten
by a reinstall, and invisible to the next person. These travel with the code they
govern, and the gates they invoke (tools/verification/) are versioned in the same
commit history. A command pointing at a guard that was never committed would be a
procedure that cannot be run by anyone else.
Invoked paths
The gates are called by real path in /experiment, /audit and /done:
python tools/verification/run_all.py
python tools/verification/gates.py --gate population --input '{"population": N, "computed_rate": R}'
python tools/verification/g5_denominator.py
Those paths are relative to the repository root, which is where an agent working in this project already is. A command that names a path which does not exist is worse than no command.
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.
- 26d ago First seen · 37 lines · 0 tokens per session scan A c592250ce87e
README is a command published in the GitHub repository ManSio/mscodebase-intelligence (3 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 378 tokens. 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 2026-10-04.
Other commands, from other repositories
index
Index a folder of documents for semantic search.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
react-native
Command "react-native" from getsentry/toolkit, covering xcode build step (react-native xcode) and important notes.
ingest-dev
Ingest a URL, directory, or file into your knowledge base. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
sugar-task
Create a comprehensive Sugar task with rich context and metadata.
resume
Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.