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 skills/phuonghx/aim-cli/skillifynpx skills add phuonghx/aim-cli --skill skillifygit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00092 | $0.00872 |
| Opus 5 | $0.00046 | $0.00436 |
| Sonnet 5 | $0.00018 | $0.00174 |
| Haiku 4.5 | $0.00009 | $0.00087 |
Grade A, and why
skillify 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 yesterday.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skillify
A procedure you repeat is a procedure worth recording once. The third time you walk the same path, pave it — write it down as a skill so the path exists for everyone after you.
Decide whether it deserves a skill
Capture it when all of these hold:
- The same flavor of task has shown up roughly three or more times.
- It has a recognizable shape: several steps that stay constant from run to run.
- It would still make sense in a different repository, not just this one.
- A fresh agent with no prior context could act on it.
Skip it when any of these apply:
- It is a single occurrence — just do the task.
- It is glue specific to one codebase — that belongs in project memory, not a shared skill.
- A skill already covers the ground — search the skills directory before adding a duplicate.
How to extract one
1. Name the invariants
Pull the pattern apart into three buckets:
- Trigger — what kicks it off (a phrase, a file type, a domain).
- Constant steps — the parts that never change between runs.
- Variable parts — what differs each time, and the shape of the result.
2. Draft the file
Keep the frontmatter to just two keys. The description does the heavy lifting: it is
how the skill gets matched later, so write it in the third person and state both what
the skill does and when to reach for it (and when not to).
---
name: kebab-case-name
description: One to a few sentences, third person, describing what the skill does and the
situations that call for it, plus what it is not for. No first person.
---
# Skill Name
A short framing line — the principle behind the skill.
## When it applies
- Conditions that should trigger it
- Conditions that should rule it out
## Procedure
### 1. First action
Concrete, do-this instructions.
### 2. Next action
...
### N. Confirm it worked
How to tell the procedure succeeded.
## Guidance
A handful of rules worth remembering.
3. Put it where skills live
.aim-agents/skills/<skill-name>/SKILL.md
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.
- yesterday First seen · 106 lines · 92 tokens per session scan A b542f9b09a9e
skillify is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 872 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
user-persona
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).