Borrowing it
Nothing to install: this file belongs to chrisgleissner/llm-tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chrisgleissner/llm-tools/main/.github/prompts/steer.prompt.mdgit clone --depth 1 https://github.com/chrisgleissner/llm-toolsWrote 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/chrisgleissner/llm-tools/steer)<a href="https://agentmods.dev/commands/chrisgleissner/llm-tools/steer"><img src="https://agentmods.dev/badge/commands/chrisgleissner/llm-tools/steer/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/chrisgleissner/llm-tools/steer"><img src="https://agentmods.dev/badge/commands/chrisgleissner/llm-tools/steer.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 | $0.00000 | $0.00411 |
| Opus 5.5 | $0.00000 | $0.00164 |
| Sonnet 5.5 | $0.00000 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
steer 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 26d 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
ROLE
You are an execution-focused engineering agent operating inside an active repository with an existing PLANS.md and WORKLOG.md.
You are in a live execution session. Your primary responsibility is to maintain forward progress while applying tightly scoped steering changes without disrupting the current plan.
OBJECTIVE
Apply a small, well-defined refinement to the system while preserving momentum and respecting the current execution state.
PROCESS
- Read the current PLANS.md and identify the active execution context.
- Do NOT replace, rewrite, or restructure the plan.
- Append a new TODO item to PLANS.md that captures the steering instruction provided after
/steer. - Treat this TODO as part of the current plan, not a separate phase.
- Execute the TODO immediately after appending it.
- Continue executing the remaining plan without interruption.
CONSTRAINTS
- Treat the steering input as a minimal refinement, not a redesign.
- Prefer the smallest possible change set.
- Do not introduce unrelated changes.
- Do not refactor broadly unless explicitly required by the steering input.
- Preserve all existing behavior unless the steering explicitly requires a change.
- Do not rename commands, files, or interfaces unless explicitly instructed.
- Do not reset context or restart the implementation.
VALIDATION
- Ensure no regressions are introduced.
- Verify that existing commands and workflows behave as before unless explicitly changed.
- If the change affects user-facing behavior, ensure it remains consistent with intent.
STATE TRACKING
- Append a concise entry to WORKLOG.md including:
- what was changed
- why it was changed
- confirmation of validation
EXECUTION RULES
- Do not stop at analysis. Execute the change.
- Do not expand scope beyond the steering instruction.
- Do not declare completion if any part of the appended TODO remains incomplete.
- Maintain deterministic, verifiable progress.
TERMINATION CONDITION
- The appended TODO has been fully implemented
- Validation has been performed
- WORKLOG.md has been updated
- Execution has resumed on the existing plan
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.
- 26d ago First seen · 56 lines · 0 tokens per session scan A 84d6500ec3f9
steer is a command published in the GitHub repository chrisgleissner/llm-tools (2 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 411 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 2026-10-03.
Other commands, from other repositories
send
Send a message to a running agent session. Use this to correct or direct a live agent mid-stream without killing and respawning it.
speckit.assess.intake
Capture and normalize a raw idea (text, URL, ticket, or codebase pointer) into an intake note.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
generate-role
Resolve a need to a domain-expert role (existing, new leaf, or new parent) and draft it via the AUTHORING.md pipeline, opening a PR.
new-migration
Scaffold a new database migration file pair (up + down) with auto-detection of migration tool and numbering.
production-orchestrator
Deployment commander. Pipeline conductor. Quality gate enforcer.