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 AleksandarBisevac/claude-plugins/plugin install auditWrote 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/aleksandarbisevac/claude-plugins/status)<a href="https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/status"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/status.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.03080 |
| Opus 5 | $0.00030 | $0.01540 |
| Sonnet 5 | $0.00012 | $0.00616 |
| Haiku 4.5 | $0.00006 | $0.00308 |
Grade A, and why
status scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit:status — pipeline status report
Run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/status/audit-status.py" <manifestPath> $ARGUMENTS
Print its stdout verbatim. Do NOT re-format, summarize, re-tabulate, or "improve" it.
It already renders the whole report: an overall line with a progress bar, the usage
line when metering is on, one aligned table across every phase (markers [x] done ·
[~] in_progress · [!] blocked · [ ] pending), what each pending task is waiting
on, a tests column carrying the verdict of the run that last exercised each task
exactly as the manifest recorded it — shown only when a task in view has recorded
one, so a plan that has never run a gate renders exactly as it did before the column
existed, and - inside it means no run was recorded, which is not a failure — the
ready-now list with a copy-pasteable /audit:run <id>, open bugs, parked
proposals when /audit:init parked any (plus a one-line footer counting free-form
legacy proposals, which /audit:propose list still reads), a BY AREA rollup when the
plan tags areas (per tag: phases and done/total tasks, - <owner> when the area
declares its advisory owner, an untagged footer, and — only when a phase actually
carries several tags — the caveat that such a phase counts under each), and a
RESUMABLE line when a phase was interrupted.
This used to be prose telling you how to lay the rollup out. That cost tokens on every
call and produced a different layout each time — the same self-defeating shape
/audit:usage already refuses. You do not need to read the manifest either: the
renderer reads it in-process, so the per-task detail that once required a second read
is in the output already.
Pass $ARGUMENTS through unchanged. --json emits the machine-readable rollup
instead, for CI or another tool.
--phase <id> scopes the human render to one phase - the table lists that phase
alone, and the render says so on a line of its own. Totals stay whole-plan: the
overall line, the usage line and the bug counts are the project's, not the phase's,
because a phase view that silently rescoped them would misreport the project. And it
does not scope the other modes - --gate evaluates its conditions over the whole
manifest and --json emits the whole rollup, whatever --phase says, so
--phase P3 --gate still gates on a task in P7. That last reading has already been got
wrong here. An id no phase carries is a usage error (exit 2) naming the ids there are.
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 Changed · +13 lines 4e65b2341d7c
- 6d ago First seen · 181 lines · 61 tokens per session scan A 04949948787f
status is a command published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 3,080 once invoked, about $0.0003 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 2026-08-31.
Other commands, from other repositories
sdlc-implement
Standalone issue implementation with Ralph Loop — implements a single Linear issue or free-form spec using fullstack-engineer + self-correcting retry loop.
sdlc
Master orchestrator for the complete 5-phase SDLC pipeline. Runs all phases sequentially with approval gates and handoffs between each phase. Organizes artifacts into handoffs/, docs/, and projects/ directories.
to-issues
Create one Linear issue per slice from an existing scope.json. Run standalone to (re)create issues without rerunning the full Plan phase. Falls back to docs/issues.md if Linear MCP is unavailable.
sdlc-plan
Phase 1 — Plan. Runs product-manager grill-me interview + slice decomposition, then publishes PRD and creates issues. Invokes exactly 1 agent.
poam-review
Review and manage Plan of Action & Milestones (POA&M).
spec
A requirements-planning command for OpenSpec, a tool that records software changes as proposals, specification updates, and task lists. It clarifies the request, challenges risky assumptions, and pauses for approval before implementation.