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 tjqscott/dory --skill loopgit clone --depth 1 https://github.com/tjqscott/doryWrote 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/tjqscott/dory/loop)<a href="https://agentmods.dev/skills/tjqscott/dory/loop"><img src="https://agentmods.dev/badge/skills/tjqscott/dory/loop/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/tjqscott/dory/loop"><img src="https://agentmods.dev/badge/skills/tjqscott/dory/loop.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 | $0.00044 | $0.00336 |
| Opus 5.5 | $0.00018 | $0.00134 |
| Sonnet 5.5 | $0.00009 | $0.00067 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
loop 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.
What it actually says
Loop
Follow AGENTS.md VI. Every prompt carries a [dory] line with the time and the five-hour usage.
- Pick the top item under
## Nowinwiki/tickets.md, or else## Next. State its check before starting. - Work it. When its check passes, run the learn skill on what it taught and move it to
## Done. - Before each new item, read the
[dory]line:- Below 90%: continue.
- 90% or more: start no model-heavy item. Finish the current one, and queue jobs that need no model under
## CPU, each with its command and output path. - 95% or more: launch every
## CPUjob in the background with its output going to a file, run the handoff skill, and start nothing else. - At 100%, Claude Code pauses and resumes after the reset (wait and continue, v2.1.234+). On resume, read the handoff first, collect the CPU outputs, and carry on from step 1.
- If usage is unknown (no statusline data), say so once and pace by the clock instead.
- Never push, merge or delete unless the project's own instructions already allow it.
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 · 19 lines · 44 tokens per session scan A 07b93e6d1b89
loop is a skill published in the GitHub repository tjqscott/dory (60 stars, last pushed 11d ago), licensed MIT. It adds 44 tokens to every session and 336 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
team-pm
PM (Project Manager / Scrum Master) agent. Reads BA and TechLead artifacts and produces sprint plan, task breakdown, and story point estimates. Creates one TodoWrite entry per sprint task for live pipeline tracking (FR-42). Part of the Virtual Team Skill pipeline.
team-list
Utility skill. Lists all projects under the projects/ directory and shows which Virtual Team pipeline phases have been completed for each project.
portfolio-manager
Plan this week's budget split between projects from the portfolio snapshot and priorities.md, then report it to the operator.
portfolio-fixture
The zero-judgement test of the portfolio flow. Copies a fixed plan to the outbox and reports it.
ax-extract-workflow
Reconstructs the workflow behind a shipped artifact from ax session evidence, commits, and PR context. Use when asking what made a feature, fix, demo, or PR work, or when turning a past success into a repeatable recipe.
himalayas-employer
AI hiring assistant for Himalayas. Post remote jobs, manage company profiles, source talent, message candidates, and benchmark salaries using the Himalayas MCP server.