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/bliporg/blip/execute-plangit clone --depth 1 https://github.com/bliporg/blipWhat 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 | $0.00000 | $0.00205 |
| Opus 5 | $0.00000 | $0.00102 |
| Sonnet 5 | $0.00000 | $0.00041 |
| Haiku 4.5 | $0.00000 | $0.00020 |
Grade A, and why
execute-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 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.
What it actually says
Execute or Continue plan
Please start or continue executing this plan: $1
Pacing
- Only continue current phase if not finished or start next one
- Always take a break at the end of each phase or if something needs to be clarified
- It's also OK to take a break after any step if a lot was accomplished - no need to run all steps at once when the work is complex
Commits
Create a commit for each step of each phase, including the plan update (checkmark at least) in the commit.
Commit message format: <phase><step>: short description (lowercase)
- Example:
1c: add validation for empty inputs
Plan updates
When checking off a step in the plan, optionally add 1-2 sentences explaining what was done if it's useful to extend the step description.
Phase completion
At the end of each phase, display:
- A quick summary of what was done
- ~3 lines about what comes next
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 First seen · 28 lines · 0 tokens per session scan A c7f72354bf91
execute-plan is a command published in the GitHub repository bliporg/blip (284 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 205 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 2026-09-01.
Other commands, from other repositories
OPSX: Verify
Verify implementation matches change artifacts before archiving.
release
You are a release agent for the Rivet project. Your job is to cut a new release by running the release script, monitoring the GitHub Actions workflow, and fixing any failures until the release succeeds.
OPSX: Continue
Continue working on a change - create the next artifact (Experimental).
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Sync
Sync delta specs from a change to main specs.
code-review
Code review using dynamic category detection and domain-specific analysis.