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 skills add arozumenko/sdlc-skills --skill knowledge-curationgit clone --depth 1 https://github.com/arozumenko/sdlc-skillsWrote 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/arozumenko/sdlc-skills/knowledge-curation)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/knowledge-curation"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/knowledge-curation.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.01826 |
| Opus 5 | $0.00049 | $0.00913 |
| Sonnet 5 | $0.00020 | $0.00365 |
| Haiku 4.5 | $0.00010 | $0.00183 |
Grade A, and why
knowledge-curation 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 8d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge curation
Two layers, one rule each:
| Layer | Scope | Tracked |
|---|---|---|
.agents/memory/<role>/ |
one role's working notes + daily log | no — gitignored, local to one machine |
.agents/knowledge/ |
distilled facts every role can use | yes — committed and reviewed |
This skill owns the second layer and the path between them. The memory skill owns the first.
Why the second layer exists. Per-role memory is local and role-scoped, so a fact one role paid for is invisible to everyone else — including the same role on another machine. Teams routinely rediscover, at great cost, something a teammate already diagnosed correctly weeks earlier. The memory was not missing and not wrong; it was unreachable. Promotion is the fix.
Admission tests — all four must hold
- Cross-role — useful to two or more roles, or architecture-level.
- Verified — confirmed against the running system; the note says how, with a date.
- Durable — still true after the current mission ends.
- Costly to rediscover — if it is obvious from reading the code, it belongs in the code.
Fail any one → leave it in .agents/memory/<role>/.
An unverified claim here is worse than silence. It is committed, so it is trusted. If you cannot state how you verified it, either verify it now or do not write it.
Keep the bar high. A thin layer that is fully trusted beats a thick one that is not.
Layout
.agents/knowledge/
├── README.md ← charter: the tests above + an index of start-here notes
├── architecture/ system shape, service boundaries, seams
├── services/ per-service invariants and surprising contracts
├── frontend/ client state, lifecycle, enforced UI rules
├── integrations/ external systems this repo depends on
├── environment/ local setup and the dev loop
├── practices/ how we work: verification, migration hazards, review focus
├── testing/ suites and harness behaviour
└── security/ credential, auth and egress invariants
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.
- 8d ago First seen · 173 lines · 99 tokens per session scan A 738be7e80423
knowledge-curation is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed 3d ago), licensed MIT. It adds 99 tokens to every session and 1,826 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.