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 skills add crimx/skills --skill stickgit clone --depth 1 https://github.com/crimx/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/skills/crimx/skills/stick)<a href="https://agentmods.dev/skills/crimx/skills/stick"><img src="https://agentmods.dev/badge/skills/crimx/skills/stick/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/skills/crimx/skills/stick"><img src="https://agentmods.dev/badge/skills/crimx/skills/stick.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 | $0.00023 | $0.00780 |
| Opus 5.5 | $0.00009 | $0.00312 |
| Sonnet 5.5 | $0.00005 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
stick 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 23d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stick
Make the supplied material easy to recall.
The supplied material is the target. Do not turn the response into a general explanation, reference entry, or open-ended lesson. Build the shortest useful path back to that target, then stop.
Core method
- State the target's core meaning or function in one short sentence.
- Preserve the target's own structure and expose only the distinctions needed to remember it.
- Add one compact memory cue when it improves retrieval. Accuracy comes first: a cue may use sound, spelling, contrast, an image, or a causal link, but an invented association must be clearly labeled as a mnemonic and never presented as factual origin or meaning.
- Add background only when it directly explains a confusing part or strengthens the memory cue. Do not add related facts, use cases, warnings, history, comparisons, or extensions merely because they are relevant.
- Stop when the target can be recalled. Do not fill a template or add optional sections for completeness.
Commands and syntax
Start with what the whole command does. Then read it left to right and preserve meaningful syntax units.
For each abbreviation, show:
| token | expansion | function |
|---|---|---|
<token> |
... | what this part does |
In expansion, bold only the letters that actually map to the full words. Map them in their actual order, including multiple letters drawn from one word; the mapping need not be one letter per word. Keep a flag with the value it governs when they form one filter or selector. Do not split a compound argument into artificial rows. Keep the bold markers outside code spans so they render. Do not repeat the letter mapping in function.
Use the table only when it makes the command easier to remember. Do not add grammar diagrams, alternative commands, or nearby variations unless the user asks for them.
Words and terminology
Start with the word's meaning in the supplied context. When the target is a word or term, check its real formation before inventing a memory cue:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago First seen · 50 lines · 23 tokens per session scan A a7523c671fbe
stick is a skill published in the GitHub repository crimx/skills (4 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 780 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 2026-10-02.
Other skills, from other repositories
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.
distill-feedback
A process for turning corrections you give an agent into lasting working rules. It reviews saved conversations and asks for approval before changing those rules.
session-explore
Investigate past AI session activity with cited catalog search, timelines, tool analytics, and bounded comparisons across providers.
reflection-injection
Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them.
session-harvest
Extract cited decisions, requirements, risks, entities, and relationships from session history and review exact candidate versions before memory promotion.