Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add kmajerowicz/get-shit-right/plugin install gsrWrote 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/kmajerowicz/get-shit-right/status)<a href="https://agentmods.dev/commands/kmajerowicz/get-shit-right/status"><img src="https://agentmods.dev/badge/commands/kmajerowicz/get-shit-right/status/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/kmajerowicz/get-shit-right/status"><img src="https://agentmods.dev/badge/commands/kmajerowicz/get-shit-right/status.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 | $0.00012 | $0.01700 |
| Opus 5.5 | $0.00005 | $0.00680 |
| Sonnet 5.5 | $0.00002 | $0.00340 |
| Haiku 4.5 | $0.00001 | $0.00170 |
Grade A, and why
status 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 12d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the /gsr:status command.
Working directory check: Use the user-intended/current project for canonical discovery. A .gsr-session.json reference is navigation only; reconcile a conflicting or stale manifest against the current task and files, never silently switch projects.
Discover canonical project and DOC_ROOT using ${CLAUDE_PLUGIN_ROOT}/lib/project.js.
Respect validated .gsr.json and report invalid configuration without silently switching
projects. Below, docs/ means the resolved DOC_ROOT. Do not run checks in a read-only
status request.
Resolve the current task before legacy fallbacks
Status-only is read-only: do not write a session manifest, run checks, implement,
execute the saved next step, or update STATE. Use $ARGUMENTS as an explicit target
when supplied: a slug resolves to DOC_ROOT/features/.md; validate a file/section
with ${CLAUDE_PLUGIN_ROOT}/lib/task-handoff.js. Otherwise use the user's current
unambiguous feature/task reference, then reconciled Active Task Plan/task.
Read Active Task by heading via ${CLAUDE_PLUGIN_ROOT}/lib/task-context.js if STATE
exists; missing STATE is valid for a focused feature. Inspect the referenced actual
spec/plan and relevant files; a task table or STATE label alone is not proof.
Conflicting/missing references are a diagnostic, never a reason to silently switch
to full-product scope. Ask for the target only when it is genuinely ambiguous.
For that task, resolve next action in this order: latest explicit user operation and
constraints → reconciled Active Task Next step/Next action → current spec/plan
and observed remaining work → legacy phase defaults below. Completed scope with
Next step: build remains a build action even if a phase table says NOT STARTED.
none does not invent a new stage. Partial/checked-increment checkpoints retain
unfinished work. A status request displays the next action without executing it.
Use saved next-step fields only when they belong to the resolved target; an obsolete Active Task for another feature cannot supply its next action.
Read open decisions from their actual owner: PRD ledger when it owns this task's
decisions, otherwise scope, or focused feature Open Decisions without either.
Follow migration references rather than counting two copies. Report assumed/deferred
IDs and relevant unresolved choices, preserving their status. Missing owner/ledger
means "decision status unknown", never "None". Only an inspected empty/resolved
owner establishes no open decisions. Do not infer human acceptance from tests.
Observe evidence read-only through ${CLAUDE_PLUGIN_ROOT}/lib/evidence.js for the
resolved project; report absent/stale/unavailable checks separately from implemented
progress. Never invoke the runner from status. Later user constraints beat saved
navigation. Do not reset implemented progress because verification is stale.
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.
- 12d ago Changed · +74 lines · -5 tokens per session af1a2afd69ed
- 2mo ago First seen · 68 lines · 17 tokens per session scan A 3aca2f731be2
status is a command published in the GitHub repository kmajerowicz/get-shit-right (6 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 1,700 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
sync-linear
Sync current work with Linear ticket status.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.