Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/marcusgoll/Spec-Flownpx agentmods add commands/marcusgoll/spec-flow/contextWrote 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/commands/marcusgoll/spec-flow/context)<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/context"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/context/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/context"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/context.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.02458 |
| Opus 5.5 | $0.00000 | $0.00983 |
| Sonnet 5.5 | $0.00000 | $0.00492 |
| Haiku 4.5 | $0.00000 | $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 1mo 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.
- 1mo ago First seen · 397 lines · 0 tokens per session scan A ea7510f9bf85
context is a command published in the GitHub repository marcusgoll/Spec-Flow (96 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,458 tokens. 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
go
A session-start command for projects whose status and task lists are kept in remote memory files. It loads the relevant project context and shows active tasks, or lists available projects when no project number is given.
setup-context
Set up your Skill Memory — a pm-context.md every skill reads so outputs come back tailored to you.
perf-difficult-conversation
Three-conversations framework rehearsal (Stone/Patton/Heen — Harvard Negotiation Project) for high-stakes conversations — termination, demotion, hard feedback, conflict surfacing. Produces three-conversations breakdown (what-happened / feelings / identity), conversation script with multiple opening choices, SCARF…
culture-onboarding-90
Design a 90-day onboarding architecture for a role. First day (psychological safety + belonging activation), first week (relationship + role context + early wins), first month (skill ramp + integration + baseline), first quarter (autonomous performance + cultural integration check). Written-first elements for…
discover-genius
Excavate genius from a person's scattered corpus. Produces Genius Profile (what only they uniquely see) + Freedom Path (four-bucket sort of every activity). Gateway to all downstream intelligence systems. For humans, not agents.
amp-download
Command "amp-download" from agentmessaging/claude-plugin, covering /amp-download, usage, arguments, options and examples.