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.
git clone --depth 1 https://github.com/KimYx0207/Meta_KimWrote 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/kimyx0207/meta_kim/meta-theory-report)<a href="https://agentmods.dev/commands/kimyx0207/meta_kim/meta-theory-report"><img src="https://agentmods.dev/badge/commands/kimyx0207/meta_kim/meta-theory-report/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/kimyx0207/meta_kim/meta-theory-report"><img src="https://agentmods.dev/badge/commands/kimyx0207/meta_kim/meta-theory-report.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 | $0.00009 | $0.00481 |
| Opus 5 | $0.00005 | $0.00241 |
| Sonnet 5 | $0.00002 | $0.00096 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
meta-theory-report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Open the user-readable report for a governed Meta_Kim run.
Run this from the installed Meta_Kim package root when the command has been rendered by global sync:
node "__META_KIM_PACKAGE_ROOT__/scripts/run-meta-theory-governed-execution.mjs" --read "${ARGUMENTS:-latest}"
If the package-root placeholder is still present and the current project is the Meta_Kim source checkout, use the source fallback:
npm run meta:theory:report -- "${ARGUMENTS:-latest}"
Report the returned status, runId, markdown report path, and selection
explanation. selectionSource is latest_committed_pointer or
explicit_run_id. selectionReason is last_committed_governed_report or
explicit_committed_run_id. Both are stable machine-readable enums.
selectionExplanation carries the human-readable explanation. In plain language:
selectionSource=latest_committed_pointermeans the newest report that finished committing; it does not mean that report is the current Claude Code host run.selectionSource=explicit_run_idmeans the requested historical/committed run was opened directly.artifactClaimStatusis the selected artifact's own claim. A validpartialreport is still readable and must not be hidden or turned into an error.different_active_runmeans canonical repository lifecycle state identifies another active run. Say that clearly, then relaynextCommandto inspect or continue it. Do not invent a report for it.unknown_invalid_projectionmeans repository lifecycle state could not be validated; a weakactive-run.jsonprojection is not current-run authority.not_checked_custom_outputmeans a custom, temporary, or external report directory was read without consulting repository lifecycle state.
Never relay task text or task fingerprints from lifecycle state. Do not claim
the run is verified unless the report itself contains fresh verification
evidence.
meta:run-status --latest --details and --json are redacted status surfaces;
use this explicit report readback when the user asks to inspect report content.
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.
- 11d ago First seen · 47 lines · 9 tokens per session scan A f106fc505f5e
meta-theory-report is a command published in the GitHub repository KimYx0207/Meta_Kim (273 stars, last pushed yesterday), licensed Apache-2.0. It adds 9 tokens to every session and 481 once invoked, about $0.0000 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 commands, from other repositories
sdd-apply
Implement SDD tasks — writes code following specs and design.
sdd-explore
Explore and investigate an idea or feature — reads codebase and compares approaches.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
gentle-sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.
constitution
A command for creating or updating a project's constitution, a document that records its governing principles and working rules, in Simplified Chinese.
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].