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 agentmods add skills/p47phoenix/claude-plugins/delivery-flownpx skills add P47Phoenix/Claude-Plugins --skill delivery-flowgit clone --depth 1 https://github.com/P47Phoenix/Claude-PluginsWrote 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/p47phoenix/claude-plugins/delivery-flow)<a href="https://agentmods.dev/skills/p47phoenix/claude-plugins/delivery-flow"><img src="https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/delivery-flow.svg" alt="Measured on agentmods" 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 | $0.00168 | $0.06741 |
| Opus 5 | $0.00084 | $0.03370 |
| Sonnet 5 | $0.00034 | $0.01348 |
| Haiku 4.5 | $0.00017 | $0.00674 |
Grade A, and why
delivery-flow 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 4d 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 — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delivery Flow Orchestrator
Design Principle
This skill is the ORCHESTRATOR. It coordinates the delivery team through a structured
pipeline but NEVER produces domain artifacts directly. All domain work — requirements,
designs, architecture, code, tests, plans — is delegated to worker skills operating as
sub-agents with isolated context. Full doctrine elaboration, Core Principles 1–7,
Anti-Patterns catalogue, and Guardrails detail: see
delivery-team/references/shared/orchestrator-doctrine.md.
Model awareness (Opus 4.7 / F-08): Under F-08, the 4.7 runtime dispatches fewer sub-agents by default unless explicitly steered. "One Role = One Sub-Agent" (Phase 4) is a behaviourally load-bearing gate, not a style preference. Role-count under-dispatch is the highest-confidence regression mode on 4.7.
Phase 0: Setup Wizard
Before the pipeline executes, check for project configuration:
State Detection (Resume Check)
Before checking config, check for an existing pipeline state:
- Check for
.delivery/state.mdin the current working directory. - If state exists with
status: in_progress:- Read the YAML frontmatter to load pipeline state.
- Announce:
> Existing pipeline found: [pipeline_id], started [date], last completed Stage [N] ([name]). Currently at Stage [N+1]. - Validate: verify all artifact files in the
artifactsmap exist on disk. If any are missing, announce which and offer: Restart from that stage / Abandon. - Semantic validation: current_stage in range 1-7, not in stages_completed, no gaps in completed+skipped.
- Config divergence check: diff
config_snapshotagainst current.delivery/config.yml. If different, warn: "Config has changed since this pipeline started. Resume uses the original config. Choose Restart to apply new config." - Offer the user: Resume / Restart / Abandon
- Resume: load config from snapshot, skip completed stages, start at current_stage.
- Restart: move state file to
.delivery/state-archive/state-<timestamp>.md(cap at 5, delete oldest), start fresh. - Abandon: delete state file, no pipeline runs.
- If state exists with
status: aborted:- Announce:
> Aborted pipeline found from [date], stopped at Stage [N]. Artifacts from stages [list] are preserved. - Offer: Resume / Restart / Abandon (same as above).
- Announce:
- If state exists with
status: completed: ignore (previous run finished normally). - If no state file exists: proceed to config check (normal flow).
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.
- references/aliases/breaking-bad.yml 9.8 KB
- references/aliases/bulls-jordan.yml 9.3 KB
- references/aliases/business.yml 2.8 KB
- references/aliases/dilbert.yml 9.3 KB
- references/aliases/funny.yml 6.7 KB
- references/aliases/lotr.yml 8.4 KB
- references/aliases/mandalorian.yml 9.3 KB
- references/aliases/marvel.yml 8.8 KB
- references/aliases/mtg.yml 8.8 KB
- references/aliases/nfl.yml 9.3 KB
- references/aliases/snl.yml 11 KB
- references/aliases/star-wars.yml 9.7 KB
- references/aliases/the-office.yml 10 KB
- references/analytics.md 6.5 KB
- references/architecture-board-personas.md 8.1 KB
- references/artifact-contracts.md 9.7 KB
- references/commands.md 1.7 KB
- references/config-keys.md 3.6 KB
- references/config-schema.json 17 KB
- references/config-schema.md 26 KB
- references/constraints-model-guide.md 7.4 KB
- references/constraints-quickstart.md 6.2 KB
- references/constraints-schema.json 2.1 KB
- references/defect-tracking.md 8.3 KB
- references/design-sprint.md 5.2 KB
- references/feature-knowledge.md 8.6 KB
- references/fixtures/constraints-dod-sample.yml 684 B
- references/fixtures/constraints-forward-compat.yml 218 B
- references/fixtures/constraints-invalid-missing-entities.yml 120 B
- references/fixtures/constraints-refine-sample.yml 894 B
- references/fixtures/constraints-valid.yml 395 B
- references/fixtures/dod-artifact-clean.md 638 B
- references/fixtures/dod-artifact-contaminated.md 620 B
- references/fixtures/dod-self-check.yml 737 B
- references/getting-started.md 9.2 KB
- references/git-integration.md 6.9 KB
- references/github-integration.md 6.1 KB
- references/manifest.yml 4.2 KB
- references/memory-protocol.md 15 KB
- references/monorepo.md 7.2 KB
- references/notifications.md 4.2 KB
- references/pipeline-scope.md 2.8 KB
- references/pipeline-stages.md 45 KB
- references/project-templates.md 7.3 KB
- references/project-types.md 9.7 KB
- references/prose-style.md 2.9 KB
- references/quality-gates.md 19 KB
- references/rules/collaboration-patterns.json 10 KB
- references/rules/dod-gates.json 20 KB
- references/rules/escalation-rules.json 9.2 KB
- references/rules/presets/solo.json 1.7 KB
- references/rules/presets/standard.json 1.0 KB
- references/rules/presets/strict.json 2.0 KB
- references/rules/stage-routing.json 44 KB
- references/setup-wizard.md 35 KB
- references/stages-schema.json 4.3 KB
- references/stages.yml 7.2 KB
- references/team-patterns.md 45 KB
- references/templates/constraints-architect.yml 3.1 KB
- references/templates/constraints-refine.yml 3.1 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.
- 4d ago First seen · 500 lines · 168 tokens per session scan A 43067c9e07e0
delivery-flow is a skill published in the GitHub repository P47Phoenix/Claude-Plugins (2 stars, last pushed 3mo ago), licensed MIT. It adds 168 tokens to every session and 6,741 once invoked, about $0.0008 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…