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/hartbrook/lookagain/tidygit clone --depth 1 https://github.com/HartBrook/lookagainWhat 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 | $0.00012 | $0.00463 |
| Opus 5 | $0.00006 | $0.00231 |
| Sonnet 5 | $0.00002 | $0.00093 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade C, and why
tidy scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
allowed-tools: Glob, Bash(rm -rf .lookagain/????-??-??T??-??-??) What it actually says
Tidy Old Review Runs
You are cleaning up old review results from .lookagain/.
Parse arguments
The user may pass key=value pairs after the command name. The raw argument string is:
$ARGUMENTS
If the argument string is empty or blank, the user provided no overrides — use all defaults. Parse key=value pairs from the string. For any key not provided, use the default.
| Key | Default | Description |
|---|---|---|
keep |
1 |
Keep runs from the last N days |
all |
false |
Remove all runs including today's (true or false) |
Process
-
Use Glob to list all directories under
.lookagain/matching the pattern.lookagain/????-??-??T??-??-??/. -
If no run directories exist, tell the user there's nothing to tidy and stop.
-
Determine which runs to remove:
- If the resolved
allvalue istrue, remove ALL run directories. - Otherwise, calculate the cutoff date by subtracting the resolved
keepvalue (in days) from today's date. Remove only run directories whose date portion (theYYYY-MM-DDprefix of the directory name) is strictly before the cutoff date.
- If the resolved
-
Before deleting, validate each directory name matches the exact pattern
YYYY-MM-DDTHH-MM-SS(all digits in the right positions). Skip any directory that doesn't match. -
For each validated run directory to remove, use Bash to delete it:
rm -rf .lookagain/<run-id> -
Report what was done:
## Tidy Complete
Removed N run(s): <list of run-ids removed>
Kept M run(s): <list of run-ids kept>
If nothing was removed, say so:
## Nothing to Tidy
All N run(s) are within the keep window.
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.
- 3d ago First seen · 54 lines · 12 tokens per session scan C cbe6fff9a0a1
tidy is a command published in the GitHub repository HartBrook/lookagain (10 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 463 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.