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/JuanMarchetto/agent-skillsWrote 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/juanmarchetto/agent-skills/forget)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/forget"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/forget.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00588 |
| Opus 5 | $0.00010 | $0.00294 |
| Sonnet 5 | $0.00004 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
forget 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forget — Remove or Archive a Lesson
You are the Learn-by-Mistake skill's lesson removal tool. The user has triggered /forget to remove or archive a specific lesson from .claude/lessons.md.
Instructions
-
Parse the argument:
- If a number is given (e.g.,
/forget 5): find lesson #5 by its number - If text is given (e.g.,
/forget docker volumes): search for matching lessons by keyword across summary, error, root cause, fix, and prevention fields - If no argument is given: ask the user which lesson to forget
- If a number is given (e.g.,
-
Find the lesson in
.claude/lessons.md:- Search in Active Lessons first, then Pending
- If multiple matches found (keyword search), list them and ask the user to pick one
- If no match found: "No lesson found matching '[argument]'. Use
/lessonsto see all lessons."
-
Show the lesson and confirm:
Found lesson to archive: ### [2026-03-10] config: Mount Docker volumes with correct permissions - **Error**: Permission denied errors inside container when writing to mounted volume - **Root cause**: Container runs as root (UID 0) but host volume is owned by a non-root user - **Fix**: Use `--user $(id -u):$(id -g)` flag or match UID/GID with host - **Prevention**: Always set user/group mapping when mounting host directories into containers - **Hits**: 3 Archive this lesson? (yes/no/delete) -
On "yes" (default): Move the lesson to the Archive section
- Add
**Archived**: [YYYY-MM-DD]to the lesson - Remove it from its current section
- Confirm: "Lesson #5 archived. It won't be applied automatically but can be restored with
/lessons search."
- Add
-
On "delete": Remove the lesson entirely
- Delete it from the file completely
- Confirm: "Lesson #5 permanently deleted."
- Warn: "This cannot be undone."
-
On "no": Cancel and do nothing.
Important
- Archived lessons are NOT deleted — they remain searchable via
/lessons search - When moving to Archive, preserve the original lesson number for reference
- If the user forgets a lesson that has high hits (>5), warn them: "This lesson has been applied [N] times. Are you sure you want to archive it?"
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.
- 4d ago First seen · 53 lines · 20 tokens per session scan A 786a89f3c8aa
forget is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 588 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 2026-09-03.
Other commands, from other repositories
phase-review
Review a phase's worktree against the spec before merging into main.
release
Cut a Uni-CLI release from a clean main.
verify
Run the full Uni-CLI verification gate and report the outcome.
context-stats
Display context window usage and token statistics.
unicli-repair
Diagnose and fix a broken Uni-CLI adapter from the original failure evidence.
unicli-search
Search any supported website or platform using Uni-CLI.