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 bostonaholic/team --skill qrspi-workflowgit clone --depth 1 https://github.com/bostonaholic/teamWrote 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/bostonaholic/team/qrspi-workflow)<a href="https://agentmods.dev/skills/bostonaholic/team/qrspi-workflow"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/qrspi-workflow/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/bostonaholic/team/qrspi-workflow"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/qrspi-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
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 →
- medium Excessive Agency · line 24 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 Agent Snooping · line 28 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 32 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 44 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 67 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 73 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00029 | $0.01240 |
| Opus 5 | $0.00015 | $0.00620 |
| Sonnet 5 | $0.00006 | $0.00248 |
| Haiku 4.5 | $0.00003 | $0.00124 |
Grade A, and why
qrspi-workflow 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 2d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QRSPI Workflow
Eight sequential phases; none are skippable:
WORKTREE -> QUESTION -> RESEARCH -> DESIGN -> STRUCTURE -> PLAN -> IMPLEMENT -> PR
Phase Sequence
| Phase | Produces | Gate |
|---|---|---|
| WORKTREE | branch <id> worktree from origin/HEAD; author docs/plans/<id>/ inside it |
HARD: exists before QUESTION |
| QUESTION | 1-task.md (full, human-only) and 2-questions.md (neutral codebase context; no goal) |
HARD: both on disk |
| RESEARCH | 5-research.md |
HARD: on disk |
| DESIGN | 6-design.md (~200 lines) and design-review-<n>.md each round |
REVIEW: APPROVE/COMMENT advance; REQUEST CHANGES redrafts and reviews again |
| STRUCTURE | 7-structure.md (~2 pages, vertical slices) |
NONE: autonomous |
| PLAN | 8-plan.md |
SOFT: no approval; reviewed design is contract |
| IMPLEMENT | code, passing tests, per-slice commits | AGGREGATE: security, verifier, code-review hard gates |
| PR | GitHub draft PR | terminal: record URL; close ledger |
WORKTREE is router-owned and has no agent; see “Why first” in skills/worktree-isolation/SKILL.md. IMPLEMENT has four sub-phases: test-architect writes failing acceptance tests; a mechanical gate requires assertion failures rather than crashes plus passing static checks, inverting to a reproduced green pre-change baseline for a zero-behavior-change refactor, whose test-architect dispatch is skipped with a recorded reason; implementer commits green slices; 5 parallel code/security/docs/ux/verifier reviews return typed failures until no Blocking/Major remains.
Artifact and isolation invariants
skills/artifact-frontmatter/SKILL.md owns <id>, inventory, 3-prd.md, 4-repos.md, topic, and ticketId schemas. Topic matches across all artifacts. 4-repos.md presence enables multi-repo; absence means single-repo. 3-prd.md is autonomous and ungated.
Research is blind (principle-blind-the-investigator). The orchestrator passes researcher/file-finder only 2-questions.md, never the description or 1-task.md; their prompts also forbid reading 1-task.md. They have Read/Grep/Glob with permissionMode: plan, so prompt adherence enforces this. Missing context becomes an open question; no user pause. Any intent leak is critical: stop and report.
What ships with it
1 file 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.
- 2d ago Changed f51ecc8802e5
- 5d ago Changed · -92 lines · -15 tokens per session 8f7a3ba46093
- 6d ago Changed · +6 lines 071da9c328e2
- 10d ago First seen · 163 lines · 44 tokens per session scan A 65c2de653633
qrspi-workflow is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 1,240 once invoked, about $0.0001 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
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
audit-trail
Full traceability from PRD to code commit through the CCPM spec-driven pipeline.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
maintenance-orchestration
Technical debt management including branch cleanup, doc verification, TODO scanning, and dependency auditing.
worktree-isolation
Manage git worktree lifecycle for safe, isolated parallel development.
github-sync
Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.