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/contextgit 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 | $0.00014 | $0.02458 |
| Opus 5 | $0.00007 | $0.01229 |
| Sonnet 5 | $0.00003 | $0.00492 |
| Haiku 4.5 | $0.00001 | $0.00246 |
Grade A, and why
context 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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/context — Consolidated Context Management
Current Directory: !pwd
TO-DOS File: !test -f TO-DOS.md && echo "exists" || echo "missing"
Active Features: !ls -d specs/*/state.yaml 2>/dev/null | wc -l || echo "0"
Session Manager: !test -f .spec-flow/scripts/bash/session-manager.sh && echo "available" || echo "missing"
/context next→ Create handoff document for continuing work in fresh context/context todos→ View and select from backlog/context add <desc>→ Add item to backlog/context status→ Show current session and workflow status
Helps maintain continuity across sessions and manage work backlog.
Step 1: Parse Action Argument
Extract first argument as action:
$action = first word of $ARGUMENTS
$remaining = rest of $ARGUMENTS
If no action provided: Use AskUserQuestion to ask:
{
"question": "What context operation do you need?",
"header": "Context Action",
"multiSelect": false,
"options": [
{
"label": "next",
"description": "Create handoff document for fresh context"
},
{
"label": "status",
"description": "Show current session and workflow status"
},
{
"label": "todos",
"description": "View and select from outstanding items"
},
{
"label": "add",
"description": "Add something to backlog"
}
]
}
Step 2: Execute Action Based on Type
<when_argument_is value="next">
Create Handoff Document
Purpose: Analyze current conversation and create handoff document for continuing work in a fresh context.
Implementation Steps:
-
Analyze current conversation:
- Review conversation history
- Identify incomplete tasks
- Extract key decisions and context
- Note any blockers or dependencies
-
Create handoff document:
- File:
HANDOFF-{timestamp}.md - Sections:
- Current State: What was being worked on
- Completed: What was finished
- In Progress: What needs continuation
- Context: Important decisions and rationale
- Next Steps: Actionable items for next session
- Files Modified: List of changed files
- Commands Used: Workflow commands executed
- File:
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 · 397 lines · 0 tokens per session scan A ea7510f9bf85
context is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 2,458 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
end-work
Complete work session with final checklist.
sync-linear
Sync current work with Linear ticket status.
start-work
Start work on a new Linear ticket with proper workflow.
dashboard
CLI status display — terse one-screen view of plan tree, active task, conflicts, freezes, token budget, recent decisions.
milestone-review
PitWay: Role-based milestone review workflow (start/brief/record/report/decide).
backlog
PitWay: Capture out-of-scope work discovered mid-task, without expanding current scope.