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/doodledood/manifest-dev/escalatenpx skills add doodledood/manifest-dev --skill escalategit clone --depth 1 https://github.com/doodledood/manifest-devWrote 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/doodledood/manifest-dev/escalate)<a href="https://agentmods.dev/skills/doodledood/manifest-dev/escalate"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/escalate.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 | $0.00061 | $0.00587 |
| Opus 5 | $0.00030 | $0.00293 |
| Sonnet 5 | $0.00012 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
escalate 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 today.
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
Receive the manifest path, selected verification mode, explicit or inherited verifier-model provenance, and affected gate ledger entries including evaluator provenance from /do. Surface that policy/provenance with the blocker evidence: the criterion (INV-G or AC ID) that can't be met, what was tried and why each attempt failed, the resolutions you see (fix path, amend the criterion, drop it, descope), and what you need from the user to unblock. Show the attempts — that is what separates this payload from "I can't" or "this is hard".
Also name any Process Guidance departed from, any deviation from the Initial Approach or the Deliverable order, any findings a gate reported below its threshold, and any gate whose bar the run read as suspect without a user to ask, with why — nothing gates on these, so this payload is where they surface when the run exits here.
A gate whose criterion misdescribes what it judges routes here too — reported by its verifier, or surfaced by execution — passing or failing, wherever /do's advance delegation does not reach the repair: the deliberately-chosen set, unclear provenance, or anything that is not a raise-only altitude repair. A gate whose criterion is right but whose bar costs more than it returns arrives the same way, carrying what recent rounds found and what another round would re-verify. Quote the report or name what execution showed, in place of attempts a passing gate does not have, and name the decision being asked for: whether the gate's text changes. That is the user's call, never the run's, which is why it arrives here rather than as an amendment.
A BLOCKED verifier verdict routes here too when a person can act on it — "awaiting human approval" names someone who can act, while "the scheduled build has not run yet" names only elapsed time — with the BLOCKED note quoted from the verifier and the suggested user action carried through. Under a caller's no-wait overlay a BLOCKED that leaves only waiting reports as pending rather than arriving here; without that overlay it waits and re-verifies instead. Pure questions about the manifest or process are answered inline by /do, not escalated.
If the user responds with a scope change rather than addressing the blocker ("change AC-X", "drop that criterion", "add a check for Y", "actually we also need Z"), invoke /define <manifest-path> to amend the manifest, then resume /do. Otherwise (user clears the blocker or supplies missing context), resume /do directly.
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.
- today Changed · -2 lines 4944c5ebd5ee
- 5d ago First seen · 18 lines · 61 tokens per session scan A 085f6084f44f
escalate is a skill published in the GitHub repository doodledood/manifest-dev (72 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 587 once invoked, about $0.0003 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
vertical-onboarding
Onboarding-and-switching playbook for SMB Product-Builder products. Defines the first-run experience that turns a prospect leaving an incumbent (ServiceTitan/Toast/Mindbody/Shopify/QuickBooks) into an activated user — import-first onboarding, the activation milestone, sample-data fallback, and the time-to-first-value…
change
Поправить готовый продукт в этой папке — одно маленькое изменение, а не стройка. Использовать, когда человек пишет /change или говорит «поправь», «добавь кнопку», «добавь поле», «добавь страницу», «измени цвет», «измени текст», «убери поле», «переименуй», «сделай чтобы…» — про то, что у него уже работает.…
create-handoff
Create handoff document for passing work to another session. ALWAYS use when the user says 'create a handoff', 'hand this off', 'save progress for later', 'I need to stop here', or when context usage is high (>60%) during implementation and work needs to continue in a fresh session.
setup-warp
Interactively configure Warp terminal as a Catalyst launcher. Checks Warp install, detects projects, interviews the user for display details (name/emoji/color/variants) and generates /.warp/tabconfigs/.toml files with session-naming and remote-control wiring. Idempotent — re-run to add or update projects.
morning-briefing
Generate a daily briefing markdown at thoughts/briefings/YYYY-MM-DD.md with six sections — Review yesterday, Surface decisions, Plan today, relay-dispatch candidates, Friction since last briefing, and Learnings since last briefing — synthesized from Linear, GitHub, Granola, Google Drive, Google Calendar, and the…
briefing-followup
Interactive walk-through of today's morning briefing. Loads the briefing markdown at thoughts/briefings/YYYY-MM-DD.md (built by morning-briefing), parses its decisions block, and walks the user through each open decision — approve / reject / defer, schedule a calendar entry, file a Linear ticket, launch a relay-ticket…