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/sistema2d/framecode-vibework/aicc-compactnpx skills add Sistema2D/FrameCode-VibeWork --skill aicc-compactgit clone --depth 1 https://github.com/Sistema2D/FrameCode-VibeWorkWrote 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/sistema2d/framecode-vibework/aicc-compact)<a href="https://agentmods.dev/skills/sistema2d/framecode-vibework/aicc-compact"><img src="https://agentmods.dev/badge/skills/sistema2d/framecode-vibework/aicc-compact.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00460 |
| Opus 5 | $0.00008 | $0.00230 |
| Sonnet 5 | $0.00003 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
aicc-compact 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.
What it actually says
Session compaction
Purpose
Capture only the state required to continue work without replaying the full conversation.
Use when
- an active governed batch is handed to another session or agent;
- work stops with meaningful unresolved state;
- a completed batch produced reusable operational context.
Do not create a session file for a trivial read-only exchange or duplicate information already canonical elsewhere.
Identity
Use id: SES-YYYYMMDD-HHMMSS-<short-id>. The short ID may be a commit prefix or random hexadecimal token. Never derive uniqueness only from “highest session number + 1”.
Suggested filename: YYYYMMDD-HHMMSS-<short-id>-<slug>.md.
Inputs
- active plan and its current state;
- actual modified files;
- validation evidence;
- open risks and next authorized action.
Non-responsibilities
- copying full files or chat transcripts into the handoff;
- inventing commit, test, publication, or completion evidence;
- treating the newest or highest sequence as relevant without checking scope;
- deleting older sessions as part of compaction.
Procedure
- Verify actual workspace and plan state.
- Create the page from
wiki/templates/TEMPLATE_SESSION_SYNTHESIS.md. - Link canonical files rather than copying their contents.
- Record decisions, failures, validation, unresolved risks, and next step.
- Add index/log entry only when the session is useful for future retrieval.
- Check ID uniqueness.
Required output
A concise, sourced handoff that distinguishes completed work, active work, blocked work, and optional next steps.
Validation and exit
- unique ID;
- no secrets or private runtime data;
- links resolve;
- plan/status matches disk state;
- no unsupported claim of commit, tag, test, or publication.
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 First seen · 70 lines · 16 tokens per session scan A 95fd9952959d
aicc-compact is a skill published in the GitHub repository Sistema2D/FrameCode-VibeWork (23 stars, last pushed 4d ago), licensed Apache-2.0. It adds 16 tokens to every session and 460 once invoked, about $0.0001 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
evaluate-pattern-adoption
Run or plan this repository's pattern-adoption evidence evaluation locally with signed-in Codex agents. Use when asked to refresh stale evidence, assess stable or exploratory patterns, evaluate one or all catalog patterns, discover possible new patterns, or prepare a reviewable evidence PR without model-backed GitHub…
glyph
Render an answer as ASCII art plus semantic emojis inline, right now, with no setup questions. Use for a fast visual take on status, comparisons, trade-offs, architecture, or any ad-hoc 'show me X visually' ask. For a full multi-artifact plan playground, use visualize-plan instead.
session-summary
Use at the end of a work session on a DAE feature, so the next session picks up cleanly. Triggers — "/engineer.session-summary", "wrap up the session", "write the session log", "I'm stopping for the day".
prepare-1-1
Prepare a 1-1 with anyone, in both directions: with YOUR manager (the topics you want to raise, what has changed since last time) or with someone YOU manage (commitments made/delegated, operational topics, KPI review). Takes a name/alias, cross-references the person's profile, the last 1-1 and the delta of recent…
pages
List or open distilled Wenlan pages from Codex by delegating to the local wenlan pages CLI. Invoked as /pages [query].
configure
Interactive wizard for OrchestKit settings: MCP servers, hook permissions, keybindings, and install presets. Use when customizing plugin behavior or managing settings.