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 commands/0xhimanshu/governor/plangit clone --depth 1 https://github.com/0xhimanshu/governorWrote 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/0xhimanshu/governor/plan)<a href="https://agentmods.dev/commands/0xhimanshu/governor/plan"><img src="https://agentmods.dev/badge/commands/0xhimanshu/governor/plan.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 5.1 | $0.00014 | $0.00286 |
| Opus 5 | $0.00007 | $0.00143 |
| Sonnet 5 | $0.00003 | $0.00057 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
plan 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 5d 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
Governor Plan
Create an implementation contract for $ARGUMENTS. This command is explicit
opt-in governance: do not implement yet.
Use bounded research when facts are current or market/design/API dependent. Keep research compact and cite sources when browsing.
Return a contract with:
- product concept and audience
- key research facts or assumptions
- brand/theme/storyline
- UI strategy and responsive states
- architecture and data model
- implementation phases
- planned files or file areas
- acceptance tests
- drift guardrails
- stop conditions
At the end, include a JSON contract block with these keys:
{
"title": "",
"goal": "",
"requirements": [],
"planned_files": [],
"acceptance_tests": [],
"drift_guardrails": [],
"stop_conditions": []
}
Also save the same JSON contract into plugin data before returning:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/governor.py" save-contract --title "SHORT TASK TITLE"
Pass the JSON on stdin. The helper generates a safe lowercase slug.
Tell the user implementation should begin only after they approve the contract.
Do not make /governor:plan a hidden prerequisite for small focused fixes.
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.
- 5d ago First seen · 51 lines · 14 tokens per session scan A 6e0ce976063d
plan is a command published in the GitHub repository 0xhimanshu/governor (133 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 286 once invoked, about $0.0001 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
benchmark
Run a TAU-bench evaluation end-to-end and present results.
list-branches
List project branches with their worktree status.
remove-branch
Remove a branch and its associated worktree.
/release
Release a new version — updates CHANGELOG, pyproject.toml, creates git tag, and pushes.
generate-rfcs
Break the PRD into sequential implementation RFCs.
test-strategy
Generate a test plan from features and RFCs.