Borrowing it
Nothing to install: this file belongs to maoxx241/vllm-ascend-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/maoxx241/vllm-ascend-workspace/main/.agents/skills/curate-workspace-knowledge/SKILL.mdgit clone --depth 1 https://github.com/maoxx241/vllm-ascend-workspaceWrote 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/skills/maoxx241/vllm-ascend-workspace/curate-workspace-knowledge)<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/curate-workspace-knowledge"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/curate-workspace-knowledge/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/curate-workspace-knowledge"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/curate-workspace-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00126 | $0.00621 |
| Opus 5.5 | $0.00050 | $0.00248 |
| Sonnet 5.5 | $0.00025 | $0.00124 |
| Haiku 4.5 | $0.00013 | $0.00062 |
Grade A, and why
curate-workspace-knowledge 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 2mo 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curate Workspace Knowledge
Keep .agents/knowledge/ as the only formal project knowledge source. Treat
.vaws-local/knowledge/candidates/ as an untracked review queue, never as a
second authoritative store.
Workflow
- Run
scripts/knowledge_curate.py list. - Inspect one candidate and its possible formal matches.
- Check that the root cause is confirmed, the original symptom was rerun, and at least one stable test, commit, issue, or PR evidence item exists.
- Choose exactly one disposition:
promotea novel candidate;mergeit into an existing entry with the same cause and scope;rejectan unsupported, transient, secret-bearing, or duplicate candidate;deprecatea stale formal entry.
- Run
.agents/scripts/knowledge_validate.pyand the owning Skill's tests. - Commit the formal knowledge change together with any regression protection.
Entry point
scripts/knowledge_curate.py provides:
list: return compact candidate summaries;inspect: return one full candidate plus possible formal matches;promote: create oneexperimentaloractiveformal entry;merge: merge evidence and occurrences into an existing formal entry;reject: archive a candidate locally without changing formal knowledge;deprecate: retain a formal entry while marking it obsolete.
Read only the reference needed for the active operation:
Rules
- Never parse or persist a full transcript.
- Never promote
inconclusiveverification. - Never promote knowledge supported only by untracked or unstable evidence.
- Require a regression test or two verified occurrences before
active. - Prefer
mergeover a new entry when cause and applicability match. - Use
--force-newonly after reviewing an identical fingerprint with a different confirmed cause. - Keep deterministic behavior in the owning Skill's scripts and tests; store only the cross-session explanation, scope, fingerprints, and evidence here.
- Do not copy upstream model-adapter lessons or profiler-local counterexamples into workspace knowledge unless the new record adds workspace-specific scope and references the upstream source.
What ships with it
6 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.
- 2mo ago First seen · 57 lines · 126 tokens per session scan A 065b3431811d
curate-workspace-knowledge is a skill published in the GitHub repository maoxx241/vllm-ascend-workspace (36 stars, last pushed 2mo ago), licensed MIT. It adds 126 tokens to every session and 621 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
curate-workspace-knowledge compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| curate-workspace-knowledgemaoxx241/vllm-ascend-workspace | Skill | 36 | 2mo ago | MIT | A | 126 | Codex |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |