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/commitgit 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 | $0.00010 | $0.01081 |
| Opus 5 | $0.00005 | $0.00541 |
| Sonnet 5 | $0.00002 | $0.00216 |
| Haiku 4.5 | $0.00001 | $0.00108 |
Grade A, and why
commit 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a git commit using the appropriate path based on your current knowledge.
Decision: Direct vs Delegate
Commit directly if you have clear context about the changes:
- You just implemented, fixed, or modified something in this conversation
- You know exactly what files changed and why
- The intent of the change is unambiguous
Delegate to haiku agent if ambiguous:
- User invoked
/ce:commitwithout prior context in this conversation - You're unsure what changes exist or their purpose
- The user is asking about changes you didn't make
Path A: Direct Commit (You Have Context)
Load the preflight-checks skill: Skill(ce:preflight-checks)
-
Preflight checks: Run preflight checks on staged files before committing. Fix formatting/lint issues, re-stage fixed files.
-
Quick verification:
git diff --cached --name-only # or git diff --name-only for unstagedConfirm the files match what you expect from your work.
-
Draft the message following Conventional Commits (schema below).
-
Execute:
git commit -m "your_header" -m "your_body" -
Handle pre-commit failure (max 3 attempts):
If
git commitfails (exit code != 0):a. Parse the error output. Identify what failed: formatting, lint, type errors, or tests.
b. Auto-fix if possible:
- Formatters: run the formatter directly (
prettier --write,black,ruff format,gofmt -w) - Linters with auto-fix:
eslint --fix,ruff check --fix - Type errors / test failures: read the error, fix the code
c. Re-stage fixed files and retry the commit.
d. After 3 failed attempts, escalate:
- Status: FAILED (after 3 attempts)
- Attempts log: what was tried each round
- Remaining errors: current error output
- Drafted message: the commit message for when errors are resolved
- Formatters: run the formatter directly (
Path B: Delegate to Haiku Agent (Ambiguous)
Invoke ce:haiku agent via Task tool with this prompt:
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 · 112 lines · 10 tokens per session scan A 0e63e9a70673
commit is a command published in the GitHub repository rileyhilliard/agentrc (3 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 1,081 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 2026-08-31.
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.