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/suspendnpx skills add lantisprime/claude-sdlc --skill suspendgit clone --depth 1 https://github.com/lantisprime/claude-sdlcWrote 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/lantisprime/claude-sdlc/suspend)<a href="https://agentmods.dev/skills/lantisprime/claude-sdlc/suspend"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/suspend.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 | $0.00062 | $0.01048 |
| Opus 5 | $0.00031 | $0.00524 |
| Sonnet 5 | $0.00012 | $0.00210 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
suspend 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 5d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Suspend — Pause SDLC Enforcement
Snapshot governance state, log the suspension, switch .enabled → .suspended. Six steps in order. No step may be skipped.
Step 1 — Guard: workflow must be enabled
Check for .claude/sdlc/.enabled.
If absent:
[SDLC] Workflow is not enabled — nothing to suspend.
Run /start to enable the workflow first.
Stop. Do not proceed.
Step 2 — Require a suspension reason
Prompt:
Reason for suspension (required): _
Hard-block if the response is empty, whitespace-only, or a single character. Re-prompt once:
A reason is required to log the suspension. Please enter a brief description: _
If the second response is also empty: print [SDLC] Suspend aborted — reason is required for audit log. and stop. Do not proceed without a reason.
Step 3 — Show active plans and unsigned gates
Read every .md file in .claude/sdlc/plans/ (exclude versioned files matching *.v[0-9]*.md). For each, check its corresponding gate file in .claude/sdlc/gates/ for unsigned status (gate file absent or missing **Signed at:** line).
Display:
Active plans:
REQ-001 add-login-page [build gate unsigned]
REQ-000 scope-setup [signed — all phases complete]
Warning: REQ-001 has an unsigned build gate.
Suspending will pause enforcement. The gate remains open until you re-enable and complete it.
Proceed? [Y/n]
If no active plans exist, omit the plan list and just show:
No active plans found.
Proceed with suspension? [Y/n]
If the user enters n or N: print [SDLC] Suspend aborted. and stop.
Step 4 — Run suspend-snapshot.sh
Call hooks/suspend-snapshot.sh suspend (relative to the plugin root, or absolute if $CLAUDE_PLUGIN_ROOT is set).
The script handles openssl availability, the gitignore check for config/tools.local.json, and manifest encryption. If the script exits non-zero or outputs an ERROR line, surface the error to the user and stop — do not rename the marker.
If the script prints Suspend aborted. Workflow remains enabled. (the openssl absent + user declined path), echo that message and stop.
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.
- 5d ago First seen · 109 lines · 62 tokens per session scan A 74dcfdc08461
suspend is a skill published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 1,048 once invoked, about $0.0003 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
setup
Guide the user through verifying Grainulator's MCP servers are running, explain what each server does, handle optional dependencies, and initialize a first sprint if none exists. Use when the plugin is first installed, when MCP servers fail to connect, or when the user asks for help setting up Grainulator.
challenge
Adversarial testing of a specific claim. Try to disprove it.
fetch
Size-efficient URL fetch with semantic extraction. Use for ad-hoc web research when you want content without the raw HTML overhead.
harvest
Sprint analytics — type distributions, stale claims, velocity, prediction scoring.
healthcheck
Fast pre-flight health check for all Grainulator MCP servers. Pings each server once, reports status in a table, and provides exact fix commands for any that are down. Use before starting any Grainulator session to avoid wasting time on MCP disconnections.
orchard
Multi-sprint orchestration — view dependency graph, dispatch next ready sprint.