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/ambient-code/platform/backend-reviewgit clone --depth 1 https://github.com/ambient-code/platformWhat 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 | $0.00042 | $0.00864 |
| Opus 5 | $0.00021 | $0.00432 |
| Sonnet 5 | $0.00008 | $0.00173 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
backend-review 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 yesterday.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Review Agent
Review backend Go code against documented conventions.
Context
Load these files before running checks:
specs/standards/backend/conventions.spec.mdspecs/standards/backend/error-handling.spec.mdspecs/standards/backend/k8s-client.spec.md
Checks
B1: No panic() in production (Blocker)
grep -rn "panic(" components/backend/ --include="*.go" | grep -v "_test.go"
Any match is a Blocker. Production code must return fmt.Errorf with context.
B2: User-scoped clients for user operations (Blocker)
In components/backend/handlers/:
DynamicClient.ResourceorK8sClientused for List/Get operations should useGetK8sClientsForRequest(c)instead- Acceptable uses: after RBAC validation for writes, token minting, cleanup
grep -rnE "DynamicClient\.|K8sClient\." components/backend/handlers/ --include="*.go" | grep -v "_test.go"
Cross-reference each match against the decision tree in K8S_CLIENT_PATTERNS.md.
B3: No direct type assertions on unstructured (Critical)
grep -rnE 'Object\["[^"]+"\]\.\(' components/backend/ --include="*.go" | grep -v "_test.go"
Must use unstructured.NestedMap, unstructured.NestedString, etc.
B4: No silent error handling (Critical)
Look for empty error handling blocks:
rg -nUP 'if err != nil \{\s*\n\s*\}' --type go --glob '!*_test.go' components/backend/
Also manually inspect if err != nil blocks for cases where the body only contains a comment (no actual handling).
B5: No internal error exposure in API responses (Major)
grep -rn 'gin.H{"error":.*fmt\.Sprintf\|gin.H{"error":.*err\.' components/backend/handlers/ --include="*.go" | grep -v "_test.go"
API responses should use generic messages. Detailed errors go to logs.
B6: No tokens in logs (Blocker)
grep -rn 'log.*[Tt]oken\b\|log.*[Ss]ecret\b' components/backend/ --include="*.go" | grep -v "len(token)\|_test.go"
Use len(token) for logging, never the token value itself.
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.
- yesterday First seen · 124 lines · 42 tokens per session scan A dbb5f5d08979
backend-review is an agent published in the GitHub repository ambient-code/platform (129 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 864 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
history-management
The runtime keeps conversation history for each agent session and sends a provider-facing working history to the model. Two complementary limits operate on different representations.
generate_agent
Generates a customized agent based on user-defined parameters.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…