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 granoflow/granoflow-mcp-server --skill granoflow-agent-workflowgit clone --depth 1 https://github.com/granoflow/granoflow-mcp-serverWrote 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/granoflow/granoflow-mcp-server/granoflow-agent-workflow)<a href="https://agentmods.dev/skills/granoflow/granoflow-mcp-server/granoflow-agent-workflow"><img src="https://agentmods.dev/badge/skills/granoflow/granoflow-mcp-server/granoflow-agent-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/granoflow/granoflow-mcp-server/granoflow-agent-workflow"><img src="https://agentmods.dev/badge/skills/granoflow/granoflow-mcp-server/granoflow-agent-workflow.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 | $0.00142 | $0.06570 |
| Opus 5 | $0.00071 | $0.03285 |
| Sonnet 5 | $0.00028 | $0.01314 |
| Haiku 4.5 | $0.00014 | $0.00657 |
Grade A, and why
granoflow-agent-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 9d 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 — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Granoflow Agent Workflow
Downstream owner for Task Work, Grill, waiting, Delivery, completion, cards, and
context after routing is clear. Call granoflow_task_orchestrator_skill first
when phase may be capture/Analysis/Planning/execution/completion-audit. Explicit
daily review → granoflow-daily-review. Project init →
granoflow_project_definition_skill. Do not quick-capture merely because text
contains “create task” when a later phase is clearly requested.
Granoflow MCP is a thin bridge to the local Granoflow app—not a code analyzer, CI fixer, or repo-automation framework.
Keyword
#granoflow-agent-workflow#task-work#task-delivery#grill
Branch Router
Pick one branch. Load refs with
granoflow_bundled_skill_reference(skillId, referenceId) before steps. Always
apply matching Hard Gates. Project-bound software turns also emit the
lifecycle board.
Language policy
- Skill and reference contract body stays English (including Hard Gates, field names, fail-closed codes, and templates).
- Public listing / npm / registry copy stays English-only.
- Runtime may accept localized trigger phrases and may use localized user-facing sample utterances when that helps the user and does not remove or weaken the English contract path for English users.
- Do not translate skill text for human reading of Skills—readers may ask an AI to translate. Do not maintain dual-language contract copies.
| User intent | Branch | Call first | Must load | Stop if |
|---|---|---|---|---|
| API/MCP connect fail | Connection First | granoflow_setup_status |
connection-first |
config write without dry-run |
| Milestone create / task into milestone | Milestone And Task Deadlines | — | milestone-and-task-deadlines |
deadline-less milestone |
| Capture from discussion | Discussed Requirement Task Capture | Orchestrator → capture |
discussed-requirement-task-capture |
multi-sentence success / invented placement |
| Today/dated/unfinished batch | Due Task Processing And Execution | Orchestrator if needed | daily-pending-task-triage, task-work-document-workflow |
execute without ledger/Grill |
| History / similar past work | Long-Term Work Memory | — | long-term-work-memory |
guessing missing records |
| Context YAML / living Project Work | Project And Milestone Context Stewardship | granoflow_project_definition_skill for init |
project-context-attachments |
software edit without context Hard Gate |
| Finish/complete task | Completing Tasks | — | task-delivery-workflow, implementation-learning-ledger |
complete without verified Work Document |
| Auth/decision/login/2FA block | Waiting For User Input | delegated-auth if envelope | waiting-for-user-input |
chat-only ask |
| Analyze/start/execute one task | Task Work And Execution | Orchestrator if unclear | task-work-document-workflow (+ template), implementation-learning-ledger |
execute before separate instruction |
| Weekly/monthly review | Review Drafting | — | review-drafting |
write without confirm |
| After-16:30 nudge | Daily Review Nudge | — | — | start review from nudge |
| Unhappy with Granoflow/MCP output | User Dissatisfaction | — | — | treat as publish/commit auth |
| Explicit daily journal/mood | (delegate) | granoflow_daily_review_skill |
daily-review skill | draft daily review here |
What ships with it
60 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.
- agents/openai.yaml 533 B
- references/acceptance-outcome-contract.md 8.7 KB
- references/app-icon-source-gate.md 5.5 KB
- references/change-impact-fanout.md 11 KB
- references/code-signing-strategy.md 6.6 KB
- references/connection-first.md 3.0 KB
- references/context-promotion-entry.md 1.5 KB
- references/daily-pending-task-triage.md 6.4 KB
- references/discussed-requirement-task-capture.md 15 KB
- references/discussion-writeback-contract.md 10 KB
- references/durable-run-plan-template.md 542 B
- references/engineering-acceptance-pack-template.md 5.1 KB
- references/engineering-acceptance-pack.md 13 KB
- references/execution-modes-and-acceptance-reports.md 6.5 KB
- references/external-skill-routing.md 13 KB
- references/full-delivery-acceptance.md 12 KB
- references/git-capability-detection.md 3.1 KB
- references/git-checkpoint-workflow.md 2.5 KB
- references/implementation-contract-semantic-replay.md 7.0 KB
- references/implementation-design-fidelity.md 8.5 KB
- references/implementation-learning-ledger.md 8.0 KB
- references/integration-test-special-requirements.md 7.2 KB
- references/knowledge-distillation-workflow.md 11 KB
- references/library-knowledge-notes.md 11 KB
- references/long-task-run-continuity.md 17 KB
- references/long-term-work-memory.md 7.3 KB
- references/markdown-html-acceptance-render.md 11 KB
- references/milestone-ai-review.md 6.3 KB
- references/milestone-and-task-deadlines.md 2.2 KB
- references/milestone-integration-acceptance.md 11 KB
- references/milestone-plan-acceptance-pack-template.md 6.1 KB
- references/milestone-plan-acceptance-pack.md 23 KB
- references/parallel-batch-merge-review-template.md 1.7 KB
- references/parallel-batch-merge-review.md 7.8 KB
- references/parallel-task-execution.md 10 KB
- references/pipeline-attachment-and-reentry.md 8.1 KB
- references/plan-design-gate.md 23 KB
- references/product-truth-sot-layers.md 3.6 KB
- references/project-context-attachments.md 11 KB
- references/project-e2e-sot-template.md 258 B
- references/project-e2e-sot.md 799 B
- references/project-interaction-style.md 4.2 KB
- references/project-lifecycle-progress-board.md 23 KB
- references/project-work-document-template.md 69 KB
- references/prototype-baseline-fit.md 7.2 KB
- references/prototype-confirmed-chrome-lock.md 6.6 KB
- references/prototype-doc-coverage.md 17 KB
- references/prototype-expression-brainstorm.md 18 KB
- references/prototype-implementation-fidelity.md 15 KB
- references/prototype-product-truth-writeback.md 8.0 KB
- references/prototype-serial-revision.md 9.4 KB
- references/requirement-intake-and-traceability.md 14 KB
- references/responsive-prototype-finalization.md 9.6 KB
- references/review-card-authoring.md 8.3 KB
- references/review-drafting.md 13 KB
- references/screen-task-portfolio-coverage.md 9.2 KB
- references/software-structural-budget.md 10.0 KB
- references/stack-realization-notes.md 5.3 KB
- references/task-analysis-execution.md 1.1 KB
- references/task-analysis-finalization.md 13 KB
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.
- 9d ago First seen · 383 lines · 142 tokens per session scan A 8e59fcbcbb28
granoflow-agent-workflow is a skill published in the GitHub repository granoflow/granoflow-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 6,570 once invoked, about $0.0007 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
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
gsd-mempalace-capture
File a phase artifact into MemPalace; mirror decision facts into its temporal KG.
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
github-ops
GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.