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/qingye-lab/rootloom/project-memorynpx skills add qingye-lab/rootloom --skill project-memorygit clone --depth 1 https://github.com/qingye-lab/rootloomWhat 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 | $0.00047 | $0.01031 |
| Opus 5 | $0.00023 | $0.00515 |
| Sonnet 5 | $0.00009 | $0.00206 |
| Haiku 4.5 | $0.00005 | $0.00103 |
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 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.
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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rootloom Memory
Keep a small, local, reviewable memory in .project-memory/. This Skill is shipped by
the separately installed rootloom-memory plugin, never by Rootloom Core. It is an
experimental engineering aid, not an authority, prerequisite, or automatic activity log.
Rules
- Query memory at task intake by the paths and intent actually in scope; do not inject the whole project history when only a few entries are relevant.
- Treat every result as a lead. Verify it against current source, tests, schemas, manifests, CI, and runtime evidence.
- Record only durable facts or explicitly labeled hypotheses that will change a future engineering decision. Do not copy task transcripts, model reasoning, raw logs, credentials, or sensitive payloads.
- Attach compact evidence references when practical. Prefer current repository paths, test names, issue/trace references, or accepted decision records over pasted evidence.
- Never initialize, record, resolve, supersede, or refresh memory silently. Every write is an explicit command followed by diff review.
- Keep accepted architecture and contract decisions in the repository's durable
decision-record convention;
decisions.jsonis only a relevant index. Maintain stable ownership and dependency rules inarchitecture.mdwith current evidence links.
Initialize
python3 <skill-dir>/scripts/project_memory.py --repo /path/to/repo init
This creates the compatible rootloom-project-memory-v1 files only when absent:
.project-memory/
├── README.md
├── architecture.md
├── known-risks.json
├── decisions.json
└── failures.json
Retrieve relevant context
Use repeatable paths plus the task intent. Context is read-only, bounded, and excludes expired, resolved, or superseded entries by default:
python3 <skill-dir>/scripts/project_memory.py --repo /path/to/repo context \
--path src/relay.py \
--query 'fix reconnect ordering' \
--limit 8
The result keeps architecture, failures, risks, and decisions as direct fields for compatibility. selection explains the query/truncation, while stale names matching historical entries that must not silently influence the current decision. Use --include-stale only when investigating history.
What ships with it
3 files 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.
- 2d ago First seen · 107 lines · 47 tokens per session scan A 47b161f33ea0
project-memory is a skill published in the GitHub repository qingye-lab/rootloom (7 stars, last pushed 20d ago), licensed MIT. It adds 47 tokens to every session and 1,031 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
audit-onboarding-proposal
Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…
improve-harness
Run one explicitly authorized, evidence-backed improvement to a repository's agent guidance, tools, runbooks, or validation. Use only when the user invokes $improve-harness or explicitly asks to improve the Harness after observed reusable agent friction. Do not use for ordinary product changes, speculative cleanup…
ai-elements
Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
product-decision-agent
中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景：产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B…
architecture-review
Use for clean architecture, modular monoliths, hexagonal boundaries, service boundaries, data flow, dependency direction, ADRs, or large feature planning.