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 widnyana/eyay-toolkits --skill bmad-sprint-rungit clone --depth 1 https://github.com/widnyana/eyay-toolkitsWrote 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/widnyana/eyay-toolkits/bmad-sprint-run)<a href="https://agentmods.dev/skills/widnyana/eyay-toolkits/bmad-sprint-run"><img src="https://agentmods.dev/badge/skills/widnyana/eyay-toolkits/bmad-sprint-run/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/widnyana/eyay-toolkits/bmad-sprint-run"><img src="https://agentmods.dev/badge/skills/widnyana/eyay-toolkits/bmad-sprint-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 55 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 4 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 10 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 10 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00085 | $0.02723 |
| Opus 5 | $0.00043 | $0.01362 |
| Sonnet 5 | $0.00017 | $0.00545 |
| Haiku 4.5 | $0.00009 | $0.00272 |
Grade A, and why
bmad-sprint-run 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 11d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BMad Sprint Runner
Autonomously execute ALL stories in ALL epics in the current sprint. Runs as a single continuous loop: no pauses between stories, no confirmation prompts, no stopping until every story reaches done or blocked.
Execution Rule
After completing ANY action (story done, story blocked, retry exhausted, story created), immediately begin the next story by returning to STEP 0. The only valid exit is STEP 7 (all stories resolved). Every other step unconditionally transitions to another step. Never ask for permission to continue.
Story State Machine
Valid story statuses: backlog | ready-for-dev | in-progress | review | done | blocked
backlog --[create-story]--> ready-for-dev
ready-for-dev --[checkpoint]--> in-progress
in-progress --[dev-story]--> review
review --[quality gate pass + review pass]--> done
review --[quality gate fail]--> in-progress (retry)
review --[retry exhausted]--> blocked
review --[decision_needed]--> blocked
ANY --[infrastructure fail]--> STOP (not blocked, sprint halts)
Invalid transitions (MUST NOT occur):
backlog-> anything other thanready-for-devdone-> anything (terminal state)blocked-> anything (terminal state for this sprint run)- Skipping
in-progress(every dev cycle must checkpoint first)
Forbidden Actions
State Safety
- FORBIDDEN: Mark a story
doneunless quality gates pass AND code review reports zerocriticalfindings - FORBIDDEN: Skip the quality gate (typecheck + tests) after dev-story
- FORBIDDEN: Skip code review after quality gate pass
- FORBIDDEN: Proceed past a failing quality gate or failing code review
- FORBIDDEN: Modify story content outside of skill invocations, EXCEPT status transitions to
blocked,ready-for-dev, orin-progress - FORBIDDEN: Invent review findings. If the review section is absent from the story file, treat as failure
- FORBIDDEN: Transition a story out of
doneorblocked
Git Safety
- FORBIDDEN: Use
git stash(removes untracked bmad artifacts) - FORBIDDEN: Push to remote (local state only)
- FORBIDDEN: Run on branch
mainormaster - FORBIDDEN: Skip recording the checkpoint hash before dev-story invocation
- FORBIDDEN: Run
git reset --hard,git checkout --,git restore, orgit clean— these destroy committed or working-tree work. A false-failing quality gate once usedgit reset --hardto wipe a completed story - FORBIDDEN: Run
rmagainst the project to "clean up" — failed stories retry by fixing forward, never by deleting - FORBIDDEN: Use
git add -A,git add ., or any bulk-staging form. Enumerate changed files withgit status --porcelainand stage each one by explicit path (git add path/to/file) - FORBIDDEN: Defer work into one large commit. Commit in small, frequent increments —
bmad-dev-storycommits per logical chunk as it works, each story finalizes at its own STEP 5g, and STEP 7 only sweeps residual state files. Never batch multiple chunks or stories into a single large commit
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 186 lines · 85 tokens per session scan A e750ce5a13a8
bmad-sprint-run is a skill published in the GitHub repository widnyana/eyay-toolkits (7 stars, last pushed 8d ago), licensed MIT. It adds 85 tokens to every session and 2,723 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
plan
Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.
work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).
new-work
Create and manage todo tracking documents for features, bugs, and multi-step tasks. Use when starting new work that benefits from a persistent record of decisions, progress, and context.
chief-operating-officer
Owns execution: how work actually gets done across the organization, including process, program management, capacity, vendors, supply chain, and service delivery. Use this when execution is the problem rather than strategy, to design or fix a process, to resolve cross-functional handoff failures, to plan capacity, to…