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 synthesisengineering/synthesis-skills --skill synthesis-knowledge-capturegit clone --depth 1 https://github.com/synthesisengineering/synthesis-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/synthesisengineering/synthesis-skills/synthesis-knowledge-capture)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-knowledge-capture"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-knowledge-capture/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/synthesisengineering/synthesis-skills/synthesis-knowledge-capture"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-knowledge-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 39 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00080 | $0.02696 |
| Opus 5 | $0.00040 | $0.01348 |
| Sonnet 5 | $0.00016 | $0.00539 |
| Haiku 4.5 | $0.00008 | $0.00270 |
Grade A, and why
synthesis-knowledge-capture 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 5d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Capture
Version 1.2.0 (2026-09-01) ships config.example.json and connects the
private routing table to the guided onboarding interview. The example uses a
synthetic private workspace and a hold-for-approval push posture; the onboarding
validator refuses a domain without its repo, tier, or bundle path.
Version 1.1.0 (2026-07-29)
A fact learned in a session and not written to the durable knowledge base is a fact lost. This skill is the disciplined path from "the agent now knows X" to "the knowledge base now knows X" — without duplicating, without overwriting a still-true fact, and without leaking a confidential fact into a shared corpus.
Why it exists
Most knowledge bases have a rule like "update source/ when you learn
something." A rule is not a workflow, and a manual rule drifts. The failure has
three shapes, all real:
- Evaporation. The corrected fact lives only in the session transcript. The next session starts blind and repeats the old mistake.
- Duplication. A naive append adds a second, contradictory concept. Now the corpus asserts two things and a reader cannot tell which is current.
- Destruction. A blind overwrite deletes a framing that was still accurate on a different axis, replacing signal with a plausible error.
The canonical trigger: an agent learns a corrected fact about a person's role. The corpus already holds several references to that person under a prior framing. Evaporation loses the correction; duplication contradicts; a blind flip destroys references that were right all along. The only safe path is: find every existing mention first, decide in place, reconcile rather than flip, cite the source. That path is this skill.
The configuration contract
All routing specifics live in a PRIVATE config the skill reads at load time:
~/.synthesis/knowledge-capture/config.json
It maps knowledge domains to a target repo, a confidentiality tier, and the OKF bundle path inside that repo; it names the confidential terms that must never reach a public repo; and it records each repo's push posture (auto, or hold-for-approval). This skill is generic and publishable; the config is neither. If the config is missing, STOP and say so — routing a fact without the routing table is guessing, and guessing about confidentiality is how a private fact ends up in a shared corpus.
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.
- 5d ago Changed · +9 lines c1a8853e378a
- 9d ago First seen · 215 lines · 80 tokens per session scan A 3d90ed8bdb65
synthesis-knowledge-capture is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed 2d ago), licensed Apache-2.0. It adds 80 tokens to every session and 2,696 once invoked, about $0.0004 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.