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/lantisprime/claude-sdlc/docsnpx skills add lantisprime/claude-sdlc --skill docsgit clone --depth 1 https://github.com/lantisprime/claude-sdlcWhat 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 | $0.00078 | $0.00685 |
| Opus 5 | $0.00039 | $0.00342 |
| Sonnet 5 | $0.00016 | $0.00137 |
| Haiku 4.5 | $0.00008 | $0.00068 |
Grade A, and why
docs 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 2d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs (Phase 8, cross-cutting)
Keep the SDLC artifact tree navigable and the traceability matrix current.
When to run
- After any phase signs a gate and the gate recorded artifact changes
- After a deployment completes
- On explicit request
Step 1 — Update the artifact index
Refresh .claude/sdlc/docs/index.md:
- List every artifact by phase with its path and last-modified date
- Flag any orphans (requirements with no test case, test cases with no implementation, etc.)
Step 2 — Traceability matrix
Refresh .claude/sdlc/docs/traceability.md:
| REQ ID | Tech Spec | Test Case(s) | Code (files/fns) | Test Run | Deploy |
|---|---|---|---|---|---|
| REQ-001 | specs/order.md | TC-001,002 | order.py::submit | 2026-... | prod |
Any empty cell is a visible gap. The human decides whether to fill or waive.
Step 3 — Changelog
Append to CHANGELOG.md in the consuming repo root (not in .claude/sdlc/), following the project's convention (Keep a Changelog / Conventional Commits style).
Step 4 — Architecture manifest
Refresh .claude/sdlc/architecture/manifest.json:
- File list with version and last-modified
- Cross-references (which spec refers to which architecture doc)
Step 5 — User-facing docs
If the change affects user-facing APIs, CLI flags, config keys, or UI flows, update the corresponding user docs. Don't leave this for later.
What this skill must NOT do
- Do not fabricate traceability. If a REQ has no test, say so in the matrix.
- Do not quietly "clean up" other docs while updating — follow surgical-edit discipline even here.
References
docs/SDLC.mdDocs
Next step hint
After updating the artifact index, pipe the next_suggestions conditions to skills/_shared/next-hint.sh and print any output:
printf '%s\n' \
'support_gate_signed|task complete — run /start or /plan to begin the next work item' \
'always|docs updated — continue with the current phase or run /start for the next work item' \
| bash skills/_shared/next-hint.sh
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.
- 2d ago First seen · 74 lines · 78 tokens per session scan A 5eb0d40ee38b
docs is a skill published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 685 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 2026-08-31.
Other skills, from other repositories
weather-fetcher
Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API.
time-skill
Display the current time in Pakistan Standard Time (PKT, UTC+5). Use when the user asks for the current time, Pakistan time, or PKT.
time-fetcher
Instructions for fetching current Dubai time via bash command.
weather-svg-creator
Creates an SVG weather card showing the current temperature for Dubai. Writes the SVG to orchestration-workflow/weather.svg and updates orchestration-workflow/output.md.
a11y-audit
../../../engineering-team/a11y-audit/skills/a11y-audit/SKILL.md.
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.