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/rileyhilliard/agentrc/executegit clone --depth 1 https://github.com/rileyhilliard/agentrcWhat 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 | $0.00008 | $0.01056 |
| Opus 5 | $0.00004 | $0.00528 |
| Sonnet 5 | $0.00002 | $0.00211 |
| Haiku 4.5 | $0.00001 | $0.00106 |
Grade A, and why
execute scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute an implementation plan using the executing-plans skill.
Load the skill first: Skill(ce:executing-plans)
Workflow
If no arguments provided ($ARGUMENTS is empty):
-
Find available plans: Search recursively for plan files regardless of folder structure:
glob ./**/plans/**/*.md glob ./**/plans/**/README.md glob ./plans/**/*.md glob ./plans/**/README.mdAlso check common alternative locations:
glob ./**/*-PLAN.md glob ./**/*-plan.mdIdentify plan files by:
- Files in any
plans/directory at any depth - Files with
-PLAN.mdor-plan.mdsuffix - Files containing
> **Status:**header pattern - For multi-file plans:
README.mdfiles that contain a phase table
- Files in any
-
Filter to incomplete plans:
- Read each plan file
- Check the
> **Status:**header - Only show plans with status
DRAFT,APPROVED, orIN_PROGRESS - Skip plans marked
COMPLETED
-
Present options: List incomplete plans with their status and a brief description (from the User Story or first line of spec).
Use
AskUserQuestionto let the user select which plan to execute:Which plan would you like to execute? - [plan-1-name] (APPROVED) - Brief description - [plan-2-name] (IN_PROGRESS) - Brief description -
Load the selected plan and proceed to execution prep below.
If plan path provided ($ARGUMENTS has a value):
-
Read the plan:
- If path ends in
.md: single-file plan - If path is a directory or ends in
/: multi-file plan, readREADME.md
- If path ends in
-
Verify plan exists and is executable:
- Check status is not
COMPLETED - If
COMPLETED, ask if user wants to re-execute
- Check status is not
Execution Prep (both paths):
-
Review the plan:
- Display the specification and success criteria
- Show the high-level task/phase breakdown
- For multi-file plans, show the phase table with current progress
-
Assess plan size and decide on worktree:
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.
- yesterday First seen · 130 lines · 8 tokens per session scan A 00d21cae2842
execute is a command published in the GitHub repository rileyhilliard/agentrc (3 stars, last pushed 6mo ago), licensed MIT. It adds 8 tokens to every session and 1,056 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.