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 doodledood/manifest-dev --skill sweep-ticketsgit 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/sweep-tickets)<a href="https://agentmods.dev/skills/doodledood/manifest-dev/sweep-tickets"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/sweep-tickets/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/doodledood/manifest-dev/sweep-tickets"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/sweep-tickets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.00943 |
| Opus 5 | $0.00032 | $0.00472 |
| Sonnet 5 | $0.00013 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
sweep-tickets 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 3d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sweep-tickets
Advance unattended Ticket work by at most one Ticket. A scheduled runner invokes this skill; the
selected Ticket still executes through run-ticket.
Read ../ticket-up/references/TICKET_CONVENTION.md, the project's venue reference, and
../ticket-up/references/AUTOMATED_EXECUTION.md before reading or changing store state.
Establish the shared store and runner
Resolve tickets/store-config.md or the project-declared equivalent. The venue must provide one
live claim surface every runner reads. A files venue spread across clones, branches, or worktrees
does not: report that it cannot safely sweep and stop without changing a Ticket.
Resolve the adapter's stable automation claim identity and any configured effort or type filter. The automation identity must be distinguishable from human assignees. Missing or ambiguous store, identity, or policy context stops before selection.
Select one Ticket
Build the eligible set before choosing a branch: open Auto Tickets that carry no escalation mark, match every configured effort or type filter, and whose dependencies are all closed. A type filter never treats an untyped Ticket as a wildcard. Leave closed, ungranted, escalated, dependency-blocked, policy-filtered, and human-assigned items untouched. Ignore tracking items and venue items that are not Tickets.
- Recover first. From the eligible set, find Tickets claimed by this automation identity. The
adapter's per-Ticket single-flight guarantees that a
run-ticketinvocation waits for any live run for that same canonical Ticket before it reaches this state. If any admitted interrupted attempt exists, recover one before considering new work. When several recovery candidates exist, use the store's explicit override or the convention's delay-loss rule to choose among them. - Otherwise start ready work. Compare the unassigned Tickets in the eligible set using the store's explicit priority override or the convention's expected-delay-loss rule. Judge current unattended end-to-end execution and landing time only when its difference materially changes what other eligible work loses by waiting. Do not infer days from traditional feature size or apply a fixed agent-speed multiplier; when plausible runtimes are all short relative to the consequences, treat them as effectively equal and use shorter duration only as a tiebreak.
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.
- 3d ago Changed · +1 lines 9e1173ed92e6
- 4d ago Changed 19c976ec9039
- 9d ago First seen · 74 lines · 64 tokens per session scan A f574ba746a83
sweep-tickets is a skill published in the GitHub repository doodledood/manifest-dev (73 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 943 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
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
opportunity-solution-tree
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a…
done-blocked
Reusable reporting contract for any agent that hands work back to the pipeline. Forces ONE of two terminal statuses (DONE or BLOCKED) with a specific evidence shape. Stops vague "probably finished" and "kind of stuck" verdicts.
outcome-roadmap
Transform an output-focused roadmap (feature list) into an outcome-focused one. Rewrites initiatives as outcome statements reflecting user and business impact. Use when a roadmap lists features instead of results, when making a roadmap more strategic, or when communicating what success looks like vs what will be built.
pm-planning
Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria. The pipeline can only orchestrate work it can see; this skill defines what "seeable work" looks like.
vertical-construction
Domain knowledge for the construction vertical (contractors, field crews) so architect and pm don't spec construction products naively. Covers the vocabulary (bid vs estimate, takeoff, retainage, change order, AIA G702/G703, lien waiver, draw schedule), the non-obvious money rules that incumbents like Procore price…