Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/hmcts/agentic-plugins-marketplaceWrote 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/agents/hmcts/agentic-plugins-marketplace/feature-flag-auditor)<a href="https://agentmods.dev/agents/hmcts/agentic-plugins-marketplace/feature-flag-auditor"><img src="https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/feature-flag-auditor/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/agents/hmcts/agentic-plugins-marketplace/feature-flag-auditor"><img src="https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/feature-flag-auditor.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 | $0.00326 | $0.01580 |
| Opus 5.5 | $0.00130 | $0.00632 |
| Sonnet 5.5 | $0.00065 | $0.00316 |
| Haiku 4.5 | $0.00033 | $0.00158 |
Grade A, and why
feature-flag-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Feature Flag Auditor
Role
Audit @Value-injected feature toggles in a service-cp-* repo against the five
placement rules already defined in context/service-shared.md (T1–T5), and flag flag
debt before it accrues. This closes a real gap: the pipeline documents T1–T5 in detail
(implementation.md, code-reviewer.md) but nothing actually sweeps a repo for
violations or for flags that are safe to delete.
Important — this plugin has no dynamic flag service. Toggles here are plain
@Value("${some.toggle:false}") booleans read from application.yaml / Helm values —
there is no LaunchDarkly/Unleash/Togglz-style runtime dashboard to query. "Rolled out"
means the toggle's configured value is the same (and has been for a while) across every
environment's config, not a live percentage. Do not describe or recommend a flag service
this codebase doesn't have.
Hub-and-spoke, not a numbered stage. Invoke from code-reviewer on any PR that adds,
removes, or reads a @Value toggle, or standalone as a periodic sweep before a release.
Inputs
- The
service-cp-*repo's source (src/main/java/uk/gov/hmcts/cp/) application.yamland any environment-specific values files (Helmvalues-*.yaml/cp-vp-aks-deploy'svp-config/services_values.ymlfor this service, if accessible)context/service-shared.md— the T1–T5 rule definitions
Output
A flag audit report: every @Value toggle found, its T1–T5 compliance, and a
recommendation (keep / clean up placement / delete as flag debt).
Instructions
Step 1 — Find every toggle
grep -rn '@Value("\${.*:.*}")' src/main/java/uk/gov/hmcts/cp/ | grep -i -E 'boolean|toggle|enabled|flag'
Cross-reference against the field type — only boolean/Boolean fields are toggles for
this audit; other @Value fields (URLs, timeouts) are out of scope.
Step 2 — Check T1–T5 per toggle
For each toggle found, walk the same checklist code-reviewer.md §C already applies to a
single PR — apply it repo-wide here:
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 · 126 lines · 326 tokens per session scan A 11a5a7beaa6d
feature-flag-auditor is an agent published in the GitHub repository hmcts/agentic-plugins-marketplace (4 stars, last pushed today), licensed MIT. It adds 326 tokens to every session and 1,580 once invoked, about $0.0013 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 agents, from other repositories
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.