graph-deploy

Stars6

Forks3

UpdatedJuly 24, 2026 at 00:01

Execute the DEPLOY phase via the `agf` CLI — release, DORA metrics, provider choice, cost proof; strictest gate (harness ≥ 70). Zero MCP

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

DiegoNogueiraDev

DiegoNogueiraDev/agf

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	graph-deploy
description	Execute the DEPLOY phase via the `agf` CLI — release, DORA metrics, provider choice, cost proof; strictest gate (harness ≥ 70). Zero MCP
triggers	["graph-deploy"]
version	2.0.0
author	auto-generated
date	"2026-06-16T00:00:00.000Z"
category	DEPLOY
phase	DEPLOY
tokens	~623
phases	["HANDOFF","LISTENING"]

graph-deploy

Release, DORA, provider choice, cost proof. Drive via the agf CLI — zero MCP. Load context with agf context <id> before changing anything.

When to Use

HANDOFF approved
Preparing a release (strictest gate: harness ≥ 70)

Mandatory Flow

agf gate deploy → agf forecast → agf metrics --simulate

Steps (DEPLOY phase)

Command	Does
`agf provider use <id>`	choose provider (openrouter/copilot/ollama)
`agf deliver "<request>" --live`	autonomous end-to-end delivery
`agf forecast`	DORA (deploy freq, lead time, CFR, MTTR)
`agf metrics --simulate`	re-price real bill under all models (cost proof)
`agf gate deploy`	DEPLOY gate (release_check + harness ≥ 70)

Workflow

Gate — agf gate deploy (release_check + harness ≥ 70)
DORA — agf forecast
Cost proof — agf metrics --simulate
Provider — agf provider use <id> (if switching for release)
Deploy — run the project deploy pipeline
Post-deploy — verify health checks, logs, metrics
Baseline — agf snapshot create (post-deploy state)
Transition — agf phase LISTENING

Exit

Release validated
Harness ≥ 70 (B)
DORA baseline saved
Cost simulation reviewed

Output Format

Phase: DEPLOY → LISTENING
Release: validated  Harness: X (≥70)
DORA: deploy Y/day, lead P85 Zh, CFR W%, MTTR Vh
Cost: re-priced under N models
Snapshot: pre + post
Status: deployed, monitoring in LISTENING

Loop link → LISTENING (graph-listening): agf learning stats. Spiral: agf savings → agf learning → next.

Anti-Patterns

Don't deploy with harness < 70 — strictest release gate
Don't ignore cost — use --simulate for proof
Don't deploy without a pre-deploy snapshot (rollback)
Don't skip post-deploy validation

Related Skills

$graph-handoff — agf skill show graph-handoff
$graph-listening — agf skill show graph-listening

Codex Notes

In Codex Plan Mode, plan only — don't mutate files.
During implementation, follow AGENTS.md and use apply_patch for manual edits.

Token Economy

Economia de tokens. Os levers compartilhados por todas as skills — --select, agf retrieve-command, agf exec chain, reuso antes de criação — vivem em _shared.md → Token Economy. Fonte única: um parágrafo repetido em trinta arquivos é o trigésimo primeiro que envelhece sozinho.

More from this repository

same repository

graph-accessibility

DiegoNogueiraDev/agf

Accessibility compliance audit using WCAG 2.2 AA standards, ARIA validation, screen reader testing, keyboard navigation, color contrast analysis, and i18n readiness

2026-07-246

graph-analyze

DiegoNogueiraDev/agf

Execute the ANALYZE phase of the lifecycle via the `agf` CLI — PRD creation, requirements, Definition of Ready (7 checks), cross-project learning

2026-07-246

graph-api-design

DiegoNogueiraDev/agf

API governance and design audit using OpenAPI/Swagger spec generation, REST maturity model, contract validation, and breaking change detection

2026-07-246

graph-architecture

DiegoNogueiraDev/agf

Architecture governance using C4 Model, ADR lifecycle, Architecture Fitness Functions, layer boundary enforcement, and drift detection

2026-07-246

graph-backlog-generation

DiegoNogueiraDev/agf

Human-in-the-loop PLANNING skill — investigates the project (graph + git + harness/gaps) and runs the whole ANALYZE→DESIGN→PLAN chain in one faceted loop to produce a COMPLETE PRD injected as graph backlog (epics, tasks, testable AC) for a separate agent to implement. Applies the project's planning methodologies — Impact Mapping + OKR per epic, JTBD, MoSCoW, WSJF/Cost-of-Delay, User Story Mapping, Example Mapping (Rules/Examples → Given-When-Then AC), SPIDR splitting, INVEST, Definition of Ready, Risk Matrix; the full catalogue lives in the skill body. Stops for the human after each complete PRD and iterates the next cycle from the project's own findings (dogfood). Does NOT implement. Triggers — graph-backlog-generation, gerar backlog, criar PRD, planejar feature, detalhar épico, novo ciclo, "plan the next thing", "what should we build next".

2026-07-246

graph-bug-hunter

DiegoNogueiraDev/agf

Automated bug discovery through static analysis, LSP diagnostics, pattern detection, regression hotspot analysis, and error catalog mining

2026-07-246

name	graph-deploy
description	Execute the DEPLOY phase via the `agf` CLI — release, DORA metrics, provider choice, cost proof; strictest gate (harness ≥ 70). Zero MCP
triggers	["graph-deploy"]
version	2.0.0
author	auto-generated
date	"2026-06-16T00:00:00.000Z"
category	DEPLOY
phase	DEPLOY
tokens	~623
phases	["HANDOFF","LISTENING"]

graph-deploy

Release, DORA, provider choice, cost proof. Drive via the agf CLI — zero MCP. Load context with agf context <id> before changing anything.

When to Use

HANDOFF approved
Preparing a release (strictest gate: harness ≥ 70)

Mandatory Flow

agf gate deploy → agf forecast → agf metrics --simulate

Steps (DEPLOY phase)

Command	Does
`agf provider use <id>`	choose provider (openrouter/copilot/ollama)
`agf deliver "<request>" --live`	autonomous end-to-end delivery
`agf forecast`	DORA (deploy freq, lead time, CFR, MTTR)
`agf metrics --simulate`	re-price real bill under all models (cost proof)
`agf gate deploy`	DEPLOY gate (release_check + harness ≥ 70)

Workflow

Gate — agf gate deploy (release_check + harness ≥ 70)
DORA — agf forecast
Cost proof — agf metrics --simulate
Provider — agf provider use <id> (if switching for release)
Deploy — run the project deploy pipeline
Post-deploy — verify health checks, logs, metrics
Baseline — agf snapshot create (post-deploy state)
Transition — agf phase LISTENING

Exit

Release validated
Harness ≥ 70 (B)
DORA baseline saved
Cost simulation reviewed

Output Format

Phase: DEPLOY → LISTENING
Release: validated  Harness: X (≥70)
DORA: deploy Y/day, lead P85 Zh, CFR W%, MTTR Vh
Cost: re-priced under N models
Snapshot: pre + post
Status: deployed, monitoring in LISTENING

Loop link → LISTENING (graph-listening): agf learning stats. Spiral: agf savings → agf learning → next.

Anti-Patterns

Don't deploy with harness < 70 — strictest release gate
Don't ignore cost — use --simulate for proof
Don't deploy without a pre-deploy snapshot (rollback)
Don't skip post-deploy validation

Related Skills

$graph-handoff — agf skill show graph-handoff
$graph-listening — agf skill show graph-listening

Codex Notes

In Codex Plan Mode, plan only — don't mutate files.
During implementation, follow AGENTS.md and use apply_patch for manual edits.

Token Economy

Economia de tokens. Os levers compartilhados por todas as skills — --select, agf retrieve-command, agf exec chain, reuso antes de criação — vivem em _shared.md → Token Economy. Fonte única: um parágrafo repetido em trinta arquivos é o trigésimo primeiro que envelhece sozinho.