Borrowing it
Nothing to install: this file belongs to brake71/1c-ssl-skills. 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/brake71/1c-ssl-skills/main/.agents/skills/latent-briefing/SKILL.mdgit clone --depth 1 https://github.com/brake71/1c-ssl-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/brake71/1c-ssl-skills/latent-briefing)<a href="https://agentmods.dev/skills/brake71/1c-ssl-skills/latent-briefing"><img src="https://agentmods.dev/badge/skills/brake71/1c-ssl-skills/latent-briefing/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/brake71/1c-ssl-skills/latent-briefing"><img src="https://agentmods.dev/badge/skills/brake71/1c-ssl-skills/latent-briefing.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00074 | $0.02570 |
| Opus 5.5 | $0.00030 | $0.01028 |
| Sonnet 5.5 | $0.00015 | $0.00514 |
| Haiku 4.5 | $0.00007 | $0.00257 |
Grade A, and why
latent-briefing 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 17d 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.
This is a copy
100% identical to latent-briefing — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Latent Briefing and KV Cache Memory Sharing
Hierarchical multi-agent systems often pay for the same context twice. The orchestrator accumulates a long reasoning trajectory, but each worker usually receives only a narrow text handoff such as a subtask prompt plus raw document slices. Passing the full trajectory fixes coverage but drives token cost up on every worker call. Summarization introduces latency and information loss. Retrieval helps with document access but does not preserve the orchestrator's evolving reasoning state.
Latent Briefing addresses this by sharing memory at the representation level rather than the text level. The core idea is to compact the orchestrator trajectory in the worker model's KV cache, keeping positions that are most relevant to the current worker task. The method builds on Attention Matching (AM) KV cache compaction and adapts it for inference-time multi-agent handoff with task-guided queries, a shared token mask across heads, and robust thresholding.
When to Activate
Activate this skill when:
- Designing orchestrator-worker or supervisor-specialist systems where workers need access to prior orchestrator state without replaying the full trajectory as text
- Evaluating alternatives to LLM summarization or RAG for cross-agent state transfer
- Implementing or studying KV cache compaction as a first-class inference primitive, not only prefix caching of identical prompts
- Debugging token explosion in recursive, hierarchical, or tool-heavy agent graphs
- Interpreting benchmarks that report worker-token savings, total-token savings, compaction overhead, and accuracy together
Do not activate this skill for adjacent work owned by other skills:
- API-only stacks where internal KV tensors are inaccessible: use
context-compression,memory-systems, ormulti-agent-patterns. - Ordinary persistent memory, entity tracking, or graph retrieval:
memory-systems. - General multi-agent topology without representation-level state sharing:
multi-agent-patterns. - Prefix caching, masking, or budget policy that does not transform KV state:
context-optimization.
What ships with it
1 file 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.
- 17d ago First seen · 168 lines · 74 tokens per session scan A d84e7abe51f0
latent-briefing is a skill published in the GitHub repository brake71/1c-ssl-skills (82 stars, last pushed 15d ago), licensed MIT. It adds 74 tokens to every session and 2,570 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to latent-briefing, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
web-test
A browser-automation tool for testing the 1C:Enterprise web client. It uses Playwright to navigate sections, fill forms, read tables and reports, and perform user actions in a browser.
skd-edit
A focused editor for 1C data composition schemas, the report definitions that describe queries, fields, filters, totals, and parameters. It changes an existing Template.xml file through specific operations.
form-edit
A tool for modifying an existing managed form in 1C by adding screen elements, fields, commands, and event handlers. Event handlers are code routines that run when something happens, such as a field changing.
cfe-borrow
A tool for borrowing existing 1C configuration objects into an extension, so the extension can alter or add to those objects.
cfe-patch-method
A generator for method interceptors in 1C extensions, which let an extension add code before or after an existing method or replace its body. It reads the original method and creates or updates the required BSL source file.
db-list
A command for listing and managing the 1C databases registered in a project's .v8-project.json file.