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 tomzx/agents --skill pdlcgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/pdlc)<a href="https://agentmods.dev/skills/tomzx/agents/pdlc"><img src="https://agentmods.dev/badge/skills/tomzx/agents/pdlc/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/tomzx/agents/pdlc"><img src="https://agentmods.dev/badge/skills/tomzx/agents/pdlc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.03765 |
| Opus 5 | $0.00015 | $0.01883 |
| Sonnet 5 | $0.00006 | $0.00753 |
| Haiku 4.5 | $0.00003 | $0.00377 |
Grade A, and why
pdlc 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 6d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Development Lifecycle
Orchestrates the full PDLC loop by invoking phase skills in sequence.
Each phase consumes the previous phase's artifact and ends in a gate (make-decision) with verdict proceed / pivot / kill.
Pass an optional phase name to enter the loop at a specific stage.
PDLC wraps SDLC: it decides whether and what to build, hands the how off to SDLC at define-acceptance, then closes the loop with launch and measurement.
When to Use /pdlc vs Individual Skills
- Use
/pdlc(with an optional phase name) when you want the orchestrator to run multiple phases, manage gates and backtracking, and maintain run state. The PDLC phase skills are internal sub-skills bundled under thispdlcskill atskills/pdlc/skills/<name>/SKILL.md. They are not individually discovered as slash commands, so only/pdlcis directly invocable; the orchestrator loads each phase by reading its file (see Load Each Phase Sub-Skill below).
Load Each Phase Sub-Skill (mandatory)
Before performing any work that belongs to a phase, read that phase's sub-skill file at skills/pdlc/skills/<name>/SKILL.md (use the Read tool) so its workflow, gates, and commit rules are in context.
Never execute a phase's actions from memory or general knowledge.
This applies at every phase transition, on every entry point and fast path.
If you reach a phase that commits, pushes, or opens a PR and its sub-skill is not yet read, read it before doing anything else, then follow its workflow.
Loop Overview
The PDLC loop — 6 phases (entry: problem → measure)
Phase 1 — Discover (divergent: find problems worth solving)
discover-problems Synthesize JTBD, interviews, and problem statements
research-market Size the market, map trends and segments
analyze-competition Map the competitive landscape and positioning gaps
frame-opportunities Build an opportunity-solution tree, scored
│
▼ GATE (make-decision: proceed / pivot / kill)
Phase 2 — Validate (converge or kill, before any build)
map-assumptions List hypotheses, beliefs, and risks ranked by leverage
design-experiment Design the cheapest decisive test (fake-door, concierge, prototype, survey)
run-experiment Execute, collect data, record a verdict
│
▼ GATE (make-decision: proceed / pivot / kill)
Phase 3 — Strategy (decide where to focus)
define-vision Product vision, target customer, positioning
set-goals OKRs, success metrics + guardrail metrics
build-roadmap Now/Next/Later, outcome-based
prioritize Rank the backlog (RICE / WSJF)
│
▼ GATE (make-decision: proceed / pivot / kill)
Phase 4 — Define (turn outcome into buildable scope)
write-prd Problem, outcomes, success criteria, non-goals
define-acceptance Acceptance contract: testable criteria (HANDOFF TO SDLC)
prototype-ux Wireframes/prototype + usability findings
│
▼ GATE (make-decision: proceed / pivot / kill) ──► SDLC owns the build
Phase 5 — Launch (go-to-market)
plan-launch Readiness checklist, timeline, channels
craft-messaging Value prop, messaging house, narratives
enable-teams Sales playbook, support runbook
set-pricing Pricing model, packaging, tiers
│
▼ GATE (make-decision: proceed / pivot / kill)
Phase 6 — Measure (close the loop)
spec-analytics Events, funnels, dashboards, guardrails
review-metrics Actuals vs goals, anomalies, health report
synthesize-feedback Aggregate support, sales, NPS, reviews
run-retrospective Keep / stop / start
sunset-product End-of-life plan (when an initiative is net-negative)
│
▼ GATE (make-decision: double-down / iterate / sunset) ──► feeds back into Discover
Cross-cutting (invoke at any point)
make-decision The gate mechanism — one decision record, reused at every transition
kill-initiative Explicit sunset-or-pivot: reallocate capacity, notify stakeholders
brief-stakeholders Exec summary, status update, stakeholder map
audit-outcomes Trace shipped outcomes back to the original problem and metrics (PDLC backpropagation)
manage-portfolio Health across multiple initiatives/products
Setup (run once per project, no dependencies on the loop)
initialize-pdlc-directory Bootstrap .pdlc/ structure and populate templates
sync-pdlc Reconcile .pdlc/ with current product reality (calls initialize if absent)
What ships with it
59 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/shared.md 14 KB
- skills/analyze-competition/SKILL.md 1.8 KB
- skills/audit-outcomes/SKILL.md 3.1 KB
- skills/brief-stakeholders/SKILL.md 2.4 KB
- skills/build-roadmap/SKILL.md 2.0 KB
- skills/craft-messaging/SKILL.md 1.9 KB
- skills/define-acceptance/SKILL.md 2.8 KB
- skills/define-vision/SKILL.md 2.0 KB
- skills/design-experiment/SKILL.md 2.1 KB
- skills/discover-problems/SKILL.md 2.3 KB
- skills/enable-teams/SKILL.md 1.8 KB
- skills/frame-opportunities/SKILL.md 2.2 KB
- skills/initialize-pdlc-directory/SKILL.md 3.8 KB
- skills/kill-initiative/SKILL.md 2.5 KB
- skills/make-decision/SKILL.md 4.2 KB
- skills/manage-portfolio/SKILL.md 2.2 KB
- skills/map-assumptions/SKILL.md 2.1 KB
- skills/pdlc-status/SKILL.md 2.2 KB
- skills/plan-launch/SKILL.md 1.9 KB
- skills/prioritize/SKILL.md 1.9 KB
- skills/prototype-ux/SKILL.md 2.1 KB
- skills/research-market/SKILL.md 1.9 KB
- skills/review-metrics/SKILL.md 2.0 KB
- skills/run-experiment/SKILL.md 2.3 KB
- skills/run-retrospective/SKILL.md 1.9 KB
- skills/set-goals/SKILL.md 2.1 KB
- skills/set-pricing/SKILL.md 2.0 KB
- skills/spec-analytics/SKILL.md 2.0 KB
- skills/sunset-product/SKILL.md 2.1 KB
- skills/sync-pdlc/SKILL.md 2.8 KB
- skills/synthesize-feedback/SKILL.md 2.5 KB
- skills/write-prd/SKILL.md 1.9 KB
- templates/context/goals.md 482 B
- templates/context/pricing.md 375 B
- templates/context/product-overview.md 385 B
- templates/context/roadmap.md 782 B
- templates/context/vision.md 494 B
- templates/context/vocabulary.md 157 B
- templates/decision.md 966 B
- templates/initiatives/acceptance-contract.md 1.1 KB
- templates/initiatives/analytics-spec.md 930 B
- templates/initiatives/assumptions.md 1.0 KB
- templates/initiatives/competitors.md 932 B
- templates/initiatives/enablement-kit.md 806 B
- templates/initiatives/eol-plan.md 892 B
- templates/initiatives/experiment-plan.md 900 B
- templates/initiatives/experiment-result.md 937 B
- templates/initiatives/feedback-loop.md 768 B
- templates/initiatives/health-report.md 804 B
- templates/initiatives/launch-plan.md 1.1 KB
- templates/initiatives/market.md 1.1 KB
- templates/initiatives/messaging.md 865 B
- templates/initiatives/opportunity-tree.md 807 B
- templates/initiatives/prd.md 675 B
- templates/initiatives/pricing.md 828 B
- templates/initiatives/problems.md 1008 B
- templates/initiatives/progress.md 1.0 KB
- templates/initiatives/prototype.md 862 B
- templates/learning.md 611 B
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.
- 6d ago First seen · 249 lines · 30 tokens per session scan A bec7ead37641
pdlc is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 3,765 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.