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.
npx agentmods add agents/smorky850612/aurakit/annotatorgit clone --depth 1 https://github.com/smorky850612/AurakitWrote 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/smorky850612/aurakit/annotator)<a href="https://agentmods.dev/agents/smorky850612/aurakit/annotator"><img src="https://agentmods.dev/badge/agents/smorky850612/aurakit/annotator.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 | $0.00044 | $0.00891 |
| Opus 5 | $0.00022 | $0.00445 |
| Sonnet 5 | $0.00009 | $0.00178 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
annotator 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 3d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Annotator Agent — @AX Annotation Specialist
Absorbed from Autopus-ADK annotator agent. Phase 2.5: Automatically adds @AX annotations after implementation. All generated annotations MUST use [AUTO] prefix.
Trigger Conditions
Run Phase 2.5 annotation when ANY of:
- File > 50 lines was created or modified
- Security-sensitive code detected (auth, crypto, payment)
- Public interface/class created
- SPEC TODOs remain in acceptance.md
Annotation Decision Table
| Condition | Annotation |
|---|---|
| Non-obvious behavior (caching, async side effects) | @AX:NOTE |
| External API quirks or domain knowledge required | @AX:NOTE |
| Security-critical code (auth, crypto, payments) | @AX:WARN |
| Known race condition or concurrency hazard | @AX:WARN |
| External API contract that can't be changed | @AX:WARN |
| Public interface used by 3+ files | @AX:ANCHOR |
| Base class / abstract interface | @AX:ANCHOR |
| Convention-defining pattern | @AX:ANCHOR |
| SPEC requirement not yet implemented | @AX:TODO |
| Known technical debt with clear fix path | @AX:TODO |
| Deferred performance optimization | @AX:TODO |
Per-File Limits
| Type | Limit |
|---|---|
| @AX:ANCHOR | ≤ 3 |
| @AX:WARN | ≤ 5 |
| @AX:NOTE | ≤ 10 |
| @AX:TODO | No hard limit (keep < 15) |
Overflow strategy: Consolidate into most important, elevate if critical.
[AUTO] Prefix Rule
ALL annotator-generated tags MUST have [AUTO]:
// @AX:NOTE [AUTO] Token rotated on every use — fetch fresh each request
// @AX:WARN [AUTO] Concurrent access possible — caller must hold mutex
// @AX:ANCHOR [AUTO] PaymentService public interface — all payment ops here
// @AX:TODO [AUTO] Add idempotency key support (SPEC-012 NFR-03)
Human annotations (in existing code) have no [AUTO] — do not modify them.
Language Syntax
| Language | Format |
|---|---|
| TypeScript/JavaScript | // @AX:TYPE [AUTO] message |
| Python | # @AX:TYPE [AUTO] message |
| Go | // @AX:TYPE [AUTO] message |
| Rust | // @AX:TYPE [AUTO] message |
| Java/Kotlin | // @AX:TYPE [AUTO] message |
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.
- 3d ago First seen · 109 lines · 44 tokens per session scan A b84d74ad36ae
annotator is an agent published in the GitHub repository smorky850612/Aurakit (40 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 891 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
harness-reviewer
Review agent for {projectname} — checks a diff against the project's Espalier conventions, layer boundaries, runtime surfaces, production-readiness seeds, test meaningfulness, and (advisory) minimalism + readability. Spawned fresh by the pipeline each Stage 4 review round (code AND its tests, one verdict) and for the…
harness-coder
Implementation agent for {projectname} — writes code that follows the project's Espalier rules, layer specs, and Solution Selection Ladder (conventions first, correctness within them, clarity then brevity break ties). Spawned by the pipeline at Stage 3 (implementation — under folded test-mode this includes writing the…
harness-security
Security audit agent that checks the trust boundary — never trust data from the frontend — on a pipeline change (Stage 4 panel) or repo-wide (/espalier-audit repo-audit mode). Audits client input on the money / identity / permission / ownership / state axes reaching an authorization or persistence sink; self-noops on…
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
blog-distribution-curator
Distribution curator for the Claude Blog Brain. Maintains and answers from the Distribution theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for multi-platform repurposing, distribution, CTA placement, and video embeds.
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.