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/lwalden/aiagentminder/setupnpx skills add lwalden/AIAgentMinder --skill setupgit clone --depth 1 https://github.com/lwalden/AIAgentMinderWhat 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 | $0.00027 | $0.01988 |
| Opus 5 | $0.00014 | $0.00994 |
| Sonnet 5 | $0.00005 | $0.00398 |
| Haiku 4.5 | $0.00003 | $0.00199 |
Grade B, and why
setup scanned grade B 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Modify `~/.claude/settings.json` — plugin hooks register themselves. How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aiagentminder:setup
One-time initialization of AIAgentMinder in the current project. Run this in the target project's repo root, NOT in the AIAgentMinder repo itself.
Inputs
- Current working directory (= target project root)
- User interaction for project identity questions
Process
1. Detect existing install
Read .claude/aiagentminder-version if it exists.
-
If present: Tell the user "AIAgentMinder is already installed (version X)." This skill is also the re-sync / upgrade path — only the version stamp and plugin-managed files (e.g.
.claude/rules/) are refreshed; user-owned files (CLAUDE.md,DECISIONS.md,BACKLOG.md,SPRINT.md,docs/strategy-roadmap.md) are preserved. If they want a newer plugin version on disk first, ask them to run/plugin update aiagentminderbefore continuing.v5.1+ upgrade cleanup. When upgrading from a pre-5.1 install, delete any leftover artifacts of the retired auto-cycle protocol if present in the project root:
.sprint-continuation.md,.sprint-continue-signal,.sprint-tool-count,.sprint-phase-guard-count. Also remove the old.claude/rules/context-cycling.mdfile (replaced bycontext-warnings.md). Userm -f— silent when the files don't exist.The bootstrap script (step 4) additionally strips any retired auto-cycle hook registrations (
context-cycle-hook.sh,session-start-continuation.sh,session-end-cycle.sh) from the project's.claude/settings.jsonand.claude/settings.local.json. Pre-5.0 installs wired these into the project's own settings; the plugin now registers hooks viahooks.json, and the leftover PreToolUse cycle hook spawns bash on every tool call and can block edits on Windows. The strip is surgical (all other hooks and settings are preserved) and idempotent. -
If absent: Continue to step 2.
2. Codebase fingerprint
Inspect the project root for stack signals (do this via Read/Glob tools, not by asking the user). Note what you find:
| Signal | Indicates |
|---|---|
package.json |
Node.js / JavaScript |
tsconfig.json + package.json |
TypeScript |
next.config.*, app/ or pages/ dir |
Next.js |
*.csproj, *.sln, global.json |
C# / .NET |
pyproject.toml, requirements.txt, setup.py |
Python |
Cargo.toml |
Rust |
go.mod |
Go |
pom.xml, build.gradle* |
Java |
Gemfile |
Ruby |
.github/workflows/*.yml |
GitHub Actions CI |
.gitlab-ci.yml |
GitLab CI |
pytest.ini, jest.config.*, xunit, etc. |
Specific test runner |
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.
- 2d ago First seen · 140 lines · 27 tokens per session scan B 469733ce1ea5
setup is a skill published in the GitHub repository lwalden/AIAgentMinder (4 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,988 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sdd-serve
Serve the SDD Builder's AI request queue: claim requests with sddnextrequest, draft the proposal, answer with sddrespondrequest. Never writes spec files — the user accepts each proposal in the builder. Use when the user asks to attend, serve or listen to the SDD board queue. / Atiende la cola de peticiones del SDD…
sdd-workflow
Guide a project with Spec-Driven Development (SDD) discipline - idea, approved spec, consistent plan, tasks, a gate that verifies approval and consent, implementation, validation, and logbook. Bilingual EN/ES. Use when the user wants to start, spec, plan, implement, or validate work with SDD, or mentions specs, plans…
predictor-hand-skill
Expert knowledge for AI forecasting — superforecasting principles, signal taxonomy, confidence calibration, reasoning chains, and accuracy tracking.
getting-started
Get started with your Open SaaS project — fetches docs, checks Wasp installation, and helps you start your database and app.
github
Interact with GitHub (issues, PRs, repos, releases) using the gh CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.
ci-cd
CI/CD pipeline expert for GitHub Actions, GitLab CI, Jenkins, and deployment automation.