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/project-memorynpx skills add phuonghx/aim-cli --skill project-memorygit 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 | $0.00038 | $0.00455 |
| Opus 5 | $0.00019 | $0.00228 |
| Sonnet 5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
project-memory 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.
What it actually says
Project Memory (aim-memory)
Memory is the cognitive backbone of AI-native development. Because LLMs are stateless by default, project context must be stored deterministically in the codebase.
1. Directory Structure
Memory is organized under the .ai-context/ directory:
.ai-context/config.json: The single source of truth for project metadata, stack, and commands..ai-context/skills/: Holds the active AIM skills..ai-context/docs/: Directory for Markdown documentation files.
2. Tasks & Progress (Task Mode)
During execution, use planning tools to log tasks:
- Maintain a structured task list in your brain directory (
task.md). - Mark tasks with
[ ](todo),[/](in-progress), and[x](completed). - Use Conventional Commits (
feat:,fix:,docs:,refactor:) when finalizing task items.
3. Documentation & Cross-Referencing
Keep documentation clean, modular, and cross-referenced:
- Task Mentions: Refer to tasks in files or commit messages using
@task-<id>. - Doc Mentions: Link to Markdown docs using
@doc/<path>. - Code Line Links: Reference specific lines using
@doc/<path>:12or ranges using@doc/<path>:10-25. - Anchors: Reference markdown sections using
@doc/<path>#section-slug.
4. Session memory policy
At the end of a session or task:
- Evaluate whether any new design decision, architecture pattern, user preference, or recurring error should be saved as persistent memory.
- Store project-specific rules in local docs or
.ai-context/config.json. - Store global user preferences in global files so they carry across sessions.
- Default to saving durable rules automatically without waiting for explicit user instructions.
- Never duplicate full documentation code blocks into memory; summarize and reference the file path instead.
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 · 40 lines · 38 tokens per session scan A f2b83eeddc8e
project-memory is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 455 once invoked, about $0.0002 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).