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 commands/raja21068/autoresearch/projectsgit clone --depth 1 https://github.com/raja21068/AutoResearchWrote 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/raja21068/autoresearch/projects)<a href="https://agentmods.dev/commands/raja21068/autoresearch/projects"><img src="https://agentmods.dev/badge/commands/raja21068/autoresearch/projects.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 | $0.00006 | $0.00113 |
| Opus 5 | $0.00003 | $0.00056 |
| Sonnet 5 | $0.00001 | $0.00023 |
| Haiku 4.5 | $0.00001 | $0.00011 |
Grade A, and why
projects 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
Projects Command
Show continuous-learning-v2 project registry and stats: $ARGUMENTS
Your Task
Run:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/continuous-learning-v2/scripts/instinct-cli.py" projects
If CLAUDE_PLUGIN_ROOT is unavailable, use:
python3 ~/.claude/skills/continuous-learning-v2/scripts/instinct-cli.py projects
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 · 24 lines · 6 tokens per session scan A bcdaa6882d0f
projects is a command published in the GitHub repository raja21068/AutoResearch (2 stars, last pushed 3mo ago), licensed MIT. It adds 6 tokens to every session and 113 once invoked, about $0.0000 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
finish-work
Command "finish-work" from DunCanYounG-1/auto-embedded, covering 1. 机械门禁（先跑，不通过不许进 review 结论）, 2. review 三层（缺一不可）, 3. 学习回流（promote，知识复利的关键）, 4. 会话记忆（journal，跨会话续上下文） and 5. 归档.
sddp-implement
Implement the current feature tasks.
sddp-tasks
Generate an actionable task list from the current plan.
handoff
Create a handoff document for seamless session continuity.
context-budget
Legacy slash-entry shim for the context-budget skill. Prefer the skill directly.
gsd-thread
Manage persistent context threads for cross-session work.