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 n-n-code/n-n-code-skills --skill agentic-sdlcgit clone --depth 1 https://github.com/n-n-code/n-n-code-skillsWrote 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/n-n-code/n-n-code-skills/agentic-sdlc)<a href="https://agentmods.dev/skills/n-n-code/n-n-code-skills/agentic-sdlc"><img src="https://agentmods.dev/badge/skills/n-n-code/n-n-code-skills/agentic-sdlc.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 5.1 | $0.00089 | $0.01259 |
| Opus 5 | $0.00044 | $0.00629 |
| Sonnet 5 | $0.00018 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
agentic-sdlc 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 today.
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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic SDLC
Own lifecycle coordination, transitions, recovery, and completion reporting. Specialists retain their engineering and artifact decisions. This process overlay guides behavior; the host, repository checks, and external systems enforce it.
Activity and authority
For assessment or planning, return findings or a proposal without implementing it. A completed assessment may contain unresolved findings. For delivery or resumption, carry the authorized outcome to its requested endpoint.
Follow the active host hierarchy, user direction, and scoped repository policy. Preserve prior authorization; ask only for a material unresolved decision or an action outside that authority. Finish authorized preparation before requesting approval so the proposal is concrete. Readiness and passing checks grant no additional authority.
Orient and select
Inspect applicable instructions, current requirements, plans, working-tree changes, affected code, and actual verification/release procedures. Resolve facts through inspection before asking questions. Establish what the next increment needs:
- outcome, acceptance, constraints, source, and requested endpoint;
- current work, prerequisites, evidence freshness, and pending decisions;
- action authority, available capabilities, limits, and remaining allowance.
Use minimum ceremony and existing artifacts. A tiny explicitly selected task needs no invented planning document or approval gate. Use lifecycle routing for stage entry, specialist ownership, fallbacks, and invalidation. Start at the earliest necessary stage whose output is absent, insufficient, or stale; preserve valid completed work.
Deliver
- Prepare an increment. Define a testable outcome, touched boundaries, prerequisites, and proof. Split for independent goals, real executor limits, or recovery needs. Preparation is not proof a prerequisite was completed.
- Implement. Use matching engineering guidance, preserve existing changes, and deliver actual behavior with relevant tests/docs. Keep product scope fixed unless an authorized decision changes it.
- Verify and review. Check the artifact against accepted behavior, required repository checks, and risk-appropriate user journeys. Investigate generated review findings before editing. Use verification and recovery for weak, failed, conflicting, or unavailable evidence. Do not weaken an oracle merely to pass; justify legitimate test corrections independently.
- Advance or repair. Advance when inputs are current, prerequisites are satisfied, required evidence is adequate, and the next action is authorized. Further repair needs new diagnostic evidence, a changed hypothesis, or a justified safe transient retry. Continue independent authorized work while another dependency waits; stop repetition without progress.
- Release if included. Follow actual procedures and release and feedback. Inspect uncertain external outcomes before retrying a write. Use authorized operational follow-up and recovery routes; a skill invocation does not create a background service.
- Report the endpoint. Distinguish implemented, verified, released, and pending work where relevant. Cite the tested revision/environment and evidence handles; name unavailable checks. If unfinished, retain useful work and the exact unmet condition, owner when known, and next action. A handoff or exhausted allowance does not make delivery complete. Feed relevant follow-ups into existing records without silently starting unrelated work.
What ships with it
7 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.
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.
- today First seen · 115 lines · 89 tokens per session scan A ab182975374a
agentic-sdlc is a skill published in the GitHub repository n-n-code/n-n-code-skills (4 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 1,259 once invoked, about $0.0004 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 2026-09-06.
Other skills, from other repositories
ship-roadmap
Found or continue a roadmap autopilot one stage per invocation. Default: human merge. --fullauto is invocation-scoped and uses the transient wrapper only after a fresh audit. Triggers: "ship-roadmap", "ship the roadmap", "autopilot this project".
workflow-status
Read-only workflow sensor: compute repository, roadmap, dependency, PR, finding, and recovery state, then emit the fixed machine envelope. Never edits. Triggers: "workflow-status", "workflow status", "what can I build next", "state of the run".
review-spec
Independent read-only review of a frozen Product half before engineering planning. Runs the exact Product checks in a clean context and returns only SPEC-REVIEW-PASS, SPEC-REVIEW-FAIL, or NEEDS-DESIGN with a content-bound receipt. Never edits the reviewed SPEC. Triggers: "review-spec", "review the spec", "review…
work-on-ticket
Fetches Jira ticket details, creates an appropriately named branch, and initiates the task planning workflow. Use when the user says "work on [TICKETID]" or similar phrases.
jira
Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…