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 makifbaysal/tasktrooper --skill deploy-templatesgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/deploy-templates)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/deploy-templates"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/deploy-templates/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/makifbaysal/tasktrooper/deploy-templates"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/deploy-templates.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 | $0.00046 | $0.00648 |
| Opus 5.5 | $0.00018 | $0.00259 |
| Sonnet 5.5 | $0.00009 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
deploy-templates 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 8d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy templates
Deploying is a defined step like build and test, not improvisation. Every environment
(stage, preprod, prod) of a repository has a deploy target: a provider, its
variables, a health URL and a rollback policy. Each provider has a template: the
workflow to write, the secrets it needs, the smoke check and the rollback.
Workflow
- A "Set up
<env>deploy" task already carries the rendered recipe in its description — start from that rather than asking the tools for it again. get_deploy_targetwith the repository id and env to re-read what this repo ships to, plus the recipe rendered with its variables, whenever you need it again mid-task.load_deploy_templatefor the full raw recipe (secrets, smoke check, rollback) when the rendered version in the task description is not enough, or the task gives no recipe (a change to an existing deploy rather than a new one) —list_deploy_templates, optionally filtered by repo kind, to see what is available first.- Write the workflow into
.github/workflows/exactly as the recipe describes. Keep theworkflow_dispatchtrigger: the board dispatches deploys by workflow file. - Name the file and the workflow's
name:per ci-cd-pipeline-authoring so the detector maps it to the right slot (stage_deploy/preprod_deploy/prod_deploy). If the slot still shows unmapped after that, say so in one comment: mapping the detected slot is the human's action, not something you can force from here.
Non-negotiables
- A deploy must verify itself. A green deploy step that never checked the service is a lie. Every deploy ends with a smoke check against the environment's health URL.
- A deploy must be reversible. Include the rollback step from the recipe (
if: failure()). If a provider cannot roll back automatically, document the exact manual command. - Wait for the rollout.
kubectl rollout status,aws ecs wait services-stableand their equivalents are what make the result honest; dropping them for speed hides crash-looping releases. - No secrets in the workflow. Use OIDC/Workload Identity Federation and repository secrets. Never commit a key file.
- Concurrency guard. One deploy per environment at a time (
concurrency.group), otherwise two releases race and the environment ends up in an undefined state. - If a required variable is missing (the rendered recipe shows
{{key — SET THIS}}), ask for it. Do not guess a project id, region or cluster name.
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.
- 8d ago First seen · 45 lines · 46 tokens per session scan A a21d4ce9a2e6
deploy-templates is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 648 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 2026-10-05.
Other skills, from other repositories
status-card-query
Create and maintain agent-authored Paperclip status cards, or compile a prose interest prompt into bounded CompanySearchQuery objects and write the first summary from the assigned Summarizer run.
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
loop-triage
Triage recent CI failures, open issues, and recent commits into a prioritized, actionable picture. Reads the prior STATE.md as memory and rewrites it. The maker half of the loop.
c31-loop
A setup guide that adds scheduled execution to the C31 agent system. It gathers five configuration choices, records them, and creates files for running the task automatically on GitHub Actions or Windows Task Scheduler.
ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.