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/dnlbox/ai-protocol/consolidate-statenpx skills add dnlbox/ai-protocol --skill consolidate-stategit clone --depth 1 https://github.com/dnlbox/ai-protocolWrote 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/dnlbox/ai-protocol/consolidate-state)<a href="https://agentmods.dev/skills/dnlbox/ai-protocol/consolidate-state"><img src="https://agentmods.dev/badge/skills/dnlbox/ai-protocol/consolidate-state.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 5.1 | $0.00021 | $0.00350 |
| Opus 5 | $0.00010 | $0.00175 |
| Sonnet 5 | $0.00004 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
consolidate-state 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 6d 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
Consolidate state
Use this skill when the user requests state consolidation.
Use this skill when BUILD_STATE.md contradicts verified reality.
Use this skill when the current state no longer fits one screen.
Do not invoke this skill on a fixed packet cadence.
Reconciliation
- Compare
BUILD_STATE.mdwith recent git history. - Compare
BUILD_STATE.mdwith current validation evidence. - Compare
BUILD_STATE.mdwith the running product when practical. - Resolve current-state contradictions in favour of verified reality.
- Preserve material unresolved findings.
- Preserve the current approved objective.
- Preserve active ownership.
- Preserve the next meaningful action.
- Remove completed procedural detail.
- Rely on git history for completed implementation detail.
- Move older milestone summaries to
Archiveonly when they remain useful.
Runtime state
- Treat a declared runtime ledger as authoritative for live worker state.
- Treat repository evidence as authoritative for implemented behaviour.
- Pause dispatch when runtime state contradicts repository evidence.
- Reconcile the contradiction before updating durable state.
- Keep live worker telemetry out of
BUILD_STATE.md.
Result
- Keep
Nowwithin one screen. - Keep one current objective in
Now. - Keep one next meaningful action in
Now. - Keep only material current decisions.
- Keep only material current blockers.
- Keep the execution frontier compact when one exists.
- Apply the consolidation within the approved objective.
- Report the resulting state boundary.
Boundaries
- Avoid changing accepted product intent.
- Avoid changing execution strategy.
- Avoid editing protocol files.
- Avoid reporting consolidation as implementation progress.
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.
- 6d ago First seen · 55 lines · 21 tokens per session scan A f7b5438d3d2a
consolidate-state is a skill published in the GitHub repository dnlbox/ai-protocol (19 stars, last pushed 27d ago), licensed MIT. It adds 21 tokens to every session and 350 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
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
moai-workflow-thinking
Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
moai-domain-uiux
UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…