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 commands/marcusgoll/spec-flow/helpgit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWhat 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 | $0.00018 | $0.01515 |
| Opus 5 | $0.00009 | $0.00758 |
| Sonnet 5 | $0.00004 | $0.00303 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
help scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/help — Context-Aware Workflow Guidance (Thin Wrapper)
v2.0 Architecture: This command analyzes state inline for speed, with detailed rendering logic in the help-agent brief.
Active Feature: !ls -td specs/[0-9]*-* 2>/dev/null | head -1 || echo "none"
State Exists: !test -f "$(ls -td specs/[0-9]*-* 2>/dev/null | head -1)/state.yaml" 2>/dev/null && echo "yes" || echo "no"
Six Contexts (mutually exclusive):
no_feature- No specs/ directory, show getting startedno_state- Feature dir exists but state.yaml missingblocked- Workflow failed, show recovery optionsmanual_gate- Waiting for approval, show checklistcomplete- All phases done, show next feature optionsactive- In progress, show current phase and next steps
Architecture: Inline analysis for fast response. Agent brief at .claude/agents/phase/help-agent.md contains rendering templates.
Step 1: Detect Context
FEATURE_DIR=$(ls -td specs/[0-9]*-* 2>/dev/null | head -1)
if [ -z "$FEATURE_DIR" ]; then
CONTEXT="no_feature"
elif [ ! -f "$FEATURE_DIR/state.yaml" ]; then
CONTEXT="no_state"
else
STATUS=$(yq eval '.workflow.status' "$FEATURE_DIR/state.yaml" 2>/dev/null || echo "unknown")
PREVIEW=$(yq eval '.workflow.manual_gates.preview.status' "$FEATURE_DIR/state.yaml" 2>/dev/null || echo "null")
STAGING=$(yq eval '.workflow.manual_gates.validate_staging.status' "$FEATURE_DIR/state.yaml" 2>/dev/null || echo "null")
if [ "$STATUS" = "failed" ]; then
CONTEXT="blocked"
elif [ "$PREVIEW" = "pending" ] || [ "$STAGING" = "pending" ]; then
CONTEXT="manual_gate"
elif [ "$STATUS" = "completed" ]; then
CONTEXT="complete"
else
CONTEXT="active"
fi
fi
echo "Context: $CONTEXT"
echo "Feature: $FEATURE_DIR"
Step 2: Render Based on Context
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 · 234 lines · 18 tokens per session scan A aad097d76a2a
help is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 1,515 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
sync-linear
Sync current work with Linear ticket status.
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
auto-run
PitWay: Manage auto-run authorization for automatic task continuation.
task-integrate
PitWay: Apply a dispatched task's worktree commit to the main tree.
milestone-list
PitWay: List every milestone with a concise one-line status.
setup
Install the claude-pace statusline bundled with this plugin.