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.
git clone --depth 1 https://github.com/erniker/understudyWrote 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/erniker/understudy/localize-project)<a href="https://agentmods.dev/commands/erniker/understudy/localize-project"><img src="https://agentmods.dev/badge/commands/erniker/understudy/localize-project/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/erniker/understudy/localize-project"><img src="https://agentmods.dev/badge/commands/erniker/understudy/localize-project.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 | $0.00028 | $0.00285 |
| Opus 5.5 | $0.00011 | $0.00114 |
| Sonnet 5.5 | $0.00006 | $0.00057 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
localize-project 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 1mo 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
The user wants this repository to have persistent, spec-driven memory instead of relying only on the machine-wide global team's session-by-session context.
Run the following from the repository root and report what it created:
understudy --docs-only --yes
This creates docs/spec.md, docs/decisions.md, docs/session-log.md,
docs/team-roster.md and a project-level understudy.yaml — real spec/ADR/
session-log tracking for this specific repo. It does not deploy or
duplicate any agent files: the team (Architect, Backend, Frontend, DevOps,
Security, QA, etc.) keeps coming from the global install.
If the user instead wants full per-project customization (different models
per role, apply_to scoping tailored to this repo's stack, project-specific
instructions instead of the shared global ones), tell them to run
understudy --here instead — it deploys the full per-project agent set on
top of whatever is already here, never removing anything.
If the understudy command is not on PATH, tell the user how to install it
(the one-liner in the project README) instead of failing silently.
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.
- 1mo ago First seen · 28 lines · 28 tokens per session scan A 366bb4ac789e
localize-project is a command published in the GitHub repository erniker/understudy (2 stars, last pushed 20d ago), licensed MIT. It adds 28 tokens to every session and 285 once invoked, about $0.0001 per session on Opus 5.5. 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
context-restore
Restore saved project context and decisions to resume a session.
context-save
Save project context, decisions, and progress for a later session.
cost-optimize
Reduce cloud costs across AWS, Azure, and GCP through rightsizing, reserved and spot capacity, storage tuning, and cost monitoring.
refactor-clean
Refactor provided code for cleanliness, maintainability, and alignment with SOLID principles and modern best practices — no over-engineering.
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
ink-art
Hand-drawn ink-on-white doodle animation — a character that draws itself then walks/dances/waves, or a deadpan contraption explainer. Vector, deterministic, rendered via HyperFrames to MP4.