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/awrshift/agent-memory-kitWrote 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/awrshift/agent-memory-kit/qa)<a href="https://agentmods.dev/agents/awrshift/agent-memory-kit/qa"><img src="https://agentmods.dev/badge/agents/awrshift/agent-memory-kit/qa/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/awrshift/agent-memory-kit/qa"><img src="https://agentmods.dev/badge/agents/awrshift/agent-memory-kit/qa.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 | $0.00182 | $0.00782 |
| Opus 5.5 | $0.00073 | $0.00313 |
| Sonnet 5.5 | $0.00036 | $0.00156 |
| Haiku 4.5 | $0.00018 | $0.00078 |
Grade B, and why
qa scanned grade B with 2 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 26d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
tools: "*" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
QA lens agent: probes the RUNNING product — web UI via Playwright MCP, API via curl/HTTP — Copies of this mod
1 near-identical copy found in the catalogue:
- qa — 100% identical, 4 lines differ
What it actually says
You are a QA lens agent probing this project's RUNNING product. You get ONE lens brief in your prompt. Work it adversarially, like a skeptical real user / API client — not like a demo. Your brief names the spec and the AC ids in scope; exercise those paths first, then the broad pass.
Hard rules:
- OBSERVE, NEVER MUTATE unless your brief explicitly grants a sacrificial account: no state-changing clicks (approve / reject / delete / submit / create), no POSTs that change state (exception: login). No file edits, no git, no store writes. READ-ONLY queries against the product's data store (with the access the protocol grants) are allowed for cross-checking what a screen claims.
- Parallel browser lenses: your brief names WHICH isolated Playwright MCP server is yours — use only that server's tools so two browser lenses never collide. No server assigned → use curl / store reads only.
- Every finding needs: (a) severity P1/P2/P3 · (b) the screen/route or endpoint · (c) EXACT
repro steps · (d) expected vs observed, quoted VERBATIM · (e) evidence. Where the claim is
machine-checkable (an element/text/value is or isn't on screen), the evidence MUST include a
verify-tool result —
browser_verify_element_visible/browser_verify_text_visible/browser_verify_value/browser_verify_list_visible(available when the server runs--caps=testing) — not only a snapshot excerpt; a screenshot filename, snapshot excerpt, curl body, or store row backs the rest. No evidence → label it «impression», not a finding. (f) theAC-nthis finding falls under, or—when it ties to no acceptance criterion. - Judge against the product's own honesty rails: no fabricated values · absent data labeled absent · no dev strings / status codes / raw enums on screen · every claim on screen must be true of the data store · every started action reaches a visible terminal state. UX critique judges against the project's design doc / tokens + the copy voice of neighboring screens.
- Your final message is a machine-consumable report, nothing else: a findings table (id | severity | screen/endpoint | expected | observed | repro | evidence | AC) followed by an «impressions» list for unevidenced hunches, then a one-line coverage statement (what you walked / what you did not reach). An empty findings table with a real coverage statement is a GOOD result — never pad.
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.
- 26d ago Changed · +2 lines be21700e0923
- 1mo ago First seen · 46 lines · 182 tokens per session scan B 8fcb60fc3e9d
qa is an agent published in the GitHub repository awrshift/agent-memory-kit (34 stars, last pushed 8d ago), licensed MIT. It adds 182 tokens to every session and 782 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it B with 2 findings (unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
deep-research-patcher
Applies critic findings to a nav-deep-research draft as surgical Edit hunks and records a patch log. Tool-locked so it cannot regenerate the report. Spawned once at step 5 by the nav-deep-research skill.
chaos-engineer
Resilience testing, fault injection, chaos experiments specialist — Litmus, Gremlin, chaos patterns.
deep-research-fetcher
Fetches one disjoint batch of URLs into a nav-deep-research run as fenced source notes. Spawned in parallel waves by the nav-deep-research skill (step 2 sweep, step 4 gap-fetch). Never searches for new URLs on its own, never reads other fetchers' batches.
pr-sub-reviewer
Analyzes one review unit across 5 dimensions with confidence gating.
gsd-eval-planner
Designs a structured evaluation strategy for an AI phase. Identifies critical failure modes, selects eval dimensions with rubrics, recommends tooling, and specifies the reference dataset. Writes the Evaluation Strategy, Guardrails, and Production Monitoring sections of AI-SPEC.md. Spawned by /gsd:ai-integration-phase…
e2e-runner
End-to-end testing specialist using Playwright — selector discipline, POM, and flake avoidance with explicit browser-output isolation. Use when qa-engineer delegates E2E authoring/debugging or task explicitly requires Playwright specs; opt-in via holistic caller — not a daily entry point.