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/alfredoperez/speckit-companionnpx agentmods add commands/alfredoperez/speckit-companion/speckit.companion.before-stepWrote 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/alfredoperez/speckit-companion/speckit.companion.before-step)<a href="https://agentmods.dev/commands/alfredoperez/speckit-companion/speckit.companion.before-step"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/speckit.companion.before-step/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/alfredoperez/speckit-companion/speckit.companion.before-step"><img src="https://agentmods.dev/badge/commands/alfredoperez/speckit-companion/speckit.companion.before-step.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 | $0.00016 | $0.00588 |
| Opus 5.5 | $0.00006 | $0.00235 |
| Sonnet 5.5 | $0.00003 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
speckit.companion.before-step 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture Step Start
Record that the step you are about to run has started, so the SpecKit Companion GUI can time it. This command runs as the before_specify, before_plan, before_tasks and before_implement lifecycle hooks and only writes state; the step's work is the core speckit.* command that invoked it.
Prerequisites
- Verify Python is available by running
python3 --version. - If
python3is not available, warn the user and skip the capture:[companion] Warning: python3 not detected; skipped .spec-context.json capture. Do not fail the host command.
Execution
Which step is starting decides what to run.
Plan, tasks or implement. Run the writer script from the repository root with that step's values:
| Step | --step |
--status |
|---|---|---|
| plan | plan |
planning |
| tasks | tasks |
tasking |
| implement | implement |
implementing |
python3 .specify/extensions/companion/scripts/write-context.py --step <step> --status <status> --kind start --by extension
The start is idempotent: when the GUI already recorded this step's start at dispatch, the call appends nothing and the earlier time stands.
Specify. Do not run the writer. The new feature directory does not exist yet, and .specify/feature.json still points at the previous spec, so a write now would land on finished work. Read the real clock and keep what it prints:
date -u +%Y-%m-%dT%H:%M:%SZ
On PowerShell: (Get-Date).ToUniversalTime().ToString("yyyy-MM-ddTHH:mm:ssZ"). The after_specify hook records it as the step's start once the directory exists. Never type a time yourself.
Graceful Degradation
The script is best-effort and never fails the host command:
- If
python3is missing, skip with the warning above. - If the active feature directory cannot be resolved, the script prints a warning to stderr and exits 0 without writing.
- If the spec is already
completedorarchived, nothing is written.
Output
On success the script prints the path it updated and the values written, e.g. [companion] Updated specs/<NNN>-<slug>/.spec-context.json (currentStep=plan, status=planning, kind=start, by=extension). The write is atomic and appends to history[] without rewriting existing entries.
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 · 50 lines · 16 tokens per session scan A e0d35850e68a
speckit.companion.before-step is a command published in the GitHub repository alfredoperez/speckit-companion (99 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 588 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-11.
Other commands, from other repositories
peachflow:create-sprint
Find unlocked tasks in the current quarter, create a new sprint with up to 10 tasks, and set up a git worktree for implementation. Starts the sprint workflow.
peachflow:implement
Execute implementation of the current sprint's tasks. Works within a sprint worktree, plans approach, implements tasks in order, and tracks progress in the graph. Uses plan mode for each task.
peachflow:discover
Start product discovery for new projects OR add new features/initiatives to existing projects. Creates BRD/PRD and populates epics in the graph.
peachflow:plan
Break down epics into user stories and tasks using Claude's native plan mode. Explores context, writes plan for approval, then creates work items.
peachflow:graph
Launch a local visualization server to view the project's work item graph. Shows epics, user stories, tasks, and their relationships in an interactive browser-based interface.
peachflow:migrate
Migrate a peachflow v2 project to v3 format. Converts sprint/task files to graph structure.