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/build)<a href="https://agentmods.dev/commands/kmajerowicz/get-shit-right/build"><img src="https://agentmods.dev/badge/commands/kmajerowicz/get-shit-right/build/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/build"><img src="https://agentmods.dev/badge/commands/kmajerowicz/get-shit-right/build.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 | $0.00014 | $0.00490 |
| Opus 5.5 | $0.00006 | $0.00196 |
| Sonnet 5.5 | $0.00003 | $0.00098 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
build 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.
What it actually says
You are running the /gsr:build command.
Project discovery: Resolve the canonical project/worktree and DOC_ROOT with ${CLAUDE_PLUGIN_ROOT}/lib/project.js and validated .gsr.json. Invocation in a subdirectory or through a symlink does not require directory confirmation. Never silently follow an obsolete session manifest to a different project. Reconcile invalid configuration; ask only if the intended project is genuinely unresolved.
Session manifest: After confirming the working directory, write .gsr-session.json in the project root:
{ "project_dir": "<absolute path>", "project_name": "<from CLAUDE.md or scope>", "last_command": "gsr:build", "timestamp": "<ISO 8601>" }
Update this file (don't recreate) if it already exists — reconcile project_dir and project_name against the canonical intended project instead of preserving stale identity; update last_command and timestamp.
Target handling: Pass $ARGUMENTS to the skill: after removing --sketch, a slug names DOC_ROOT/features/<slug>.md and a DOC_ROOT-relative file names the exact spec. Without an explicit target use the latest request or unambiguous saved Active Task. A sufficient feature spec works without PRD/STATE; do not ask for another feature choice or force whole-product PRD preparation. Validate references through the existing task-handoff helper.
Flag handling: If invoked as /gsr:build --sketch, set FORCE_SKETCH=true before loading the skill so Step 2.5 prepares the artifact regardless of the heuristic; it does not imply another approval gate.
Load and execute the build skill: read ${CLAUDE_PLUGIN_ROOT}/skills/build/SKILL.md in full, then follow its instructions exactly.
At the build stage boundary, report actual outcome, brief verification and unresolved limits, save the exact next action/task reference and recommend /clear, then "dalej". Continue authorized work within the current stage; long builds may hand off checked partial checkpoints with remaining progress explicit. Direct verification/build commands remain optional controls. Human acceptance is separate; no automatic reset or reapproval.
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 · +1 lines · -4 tokens per session 9f812c043616
- 2mo ago First seen · 22 lines · 18 tokens per session scan A 62e3744b2d3e
build is a command published in the GitHub repository kmajerowicz/get-shit-right (6 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 490 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.