Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gotempsh/tempsnpx agentmods add skills/gotempsh/temps/temps-add-handlerWrote 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/skills/gotempsh/temps/temps-add-handler)<a href="https://agentmods.dev/skills/gotempsh/temps/temps-add-handler"><img src="https://agentmods.dev/badge/skills/gotempsh/temps/temps-add-handler/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/skills/gotempsh/temps/temps-add-handler"><img src="https://agentmods.dev/badge/skills/gotempsh/temps/temps-add-handler.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 | $0.00090 | $0.02713 |
| Opus 5.5 | $0.00036 | $0.01085 |
| Sonnet 5.5 | $0.00018 | $0.00543 |
| Haiku 4.5 | $0.00009 | $0.00271 |
Grade A, and why
temps-add-handler scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Never `curl ... > apps/temps-cli/openapi.json`: the committed file is sorted and How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add an HTTP handler
Handlers are the thin HTTP layer: authenticate, authorise, call one service, audit the write, map the result. Everything else lives in the service.
Reference crate: crates/temps-flags (small, complete, follows every rule):
| Piece | File |
|---|---|
Domain error enum + From<sea_orm::DbErr> |
crates/temps-flags/src/error.rs |
| Service (business logic, mock-DB tests) | crates/temps-flags/src/services/flag_service.rs |
| DTOs + handler state | crates/temps-flags/src/handlers/types.rs |
Handlers, routes, ApiDoc, From<FlagError> for Problem, guard tests |
crates/temps-flags/src/handlers/handler.rs |
| Audit event types | crates/temps-flags/src/handlers/audit.rs |
| Plugin wiring | crates/temps-flags/src/plugin.rs |
Read first: AGENTS.md (Errors, Architecture), REVIEW.md
→ "Authorization and scope" and "Secrets must not reach logs".
1. Service first
If the behaviour does not exist in a service yet, add it there: a method on the
crate's service struct returning Result<T, DomainError> (a thiserror enum
whose variants carry the IDs involved). No anyhow in services. The handler
never imports sea_orm or touches an entity; scripts/rule_drift.py counts
handler_db_access for any use sea_orm / Entity::find in handlers/ or
handlers.rs.
2. DTOs
In the crate's handlers/types.rs (or next to the handler):
- Request and response structs derive
Serialize/Deserializeandutoipa::ToSchema; query structs deriveutoipa::IntoParams. - Never return
Json<serde_json::Value>; always a typed struct. - Convert models to responses with
From/a constructor; do not serialise entities directly. - Dates are
DateTime<Utc>(ISO 8601 withZ). - Secrets: a stored key, token or password is never returned. Return a flag
such as
has_secret: bool(crates/temps-webhooks/src/handlers.rs) or***. The only exception is a credential minted by this request (a new API key, a reset password): returned once, withCache-Control: no-store, never logged or audited; seereset_user_passwordincrates/temps-auth/src/handlers.rs. - Lists are paginated:
page(default 1),page_size(default 20, max 100), sortedcreated_atDESC unless the domain has a better natural order. Clamp in one shared helper, asnormalize_paginationin the flags service does, so the handler'stotal_pagesmatches what the service served.
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 Changed 74322c64ecb4
- 4d ago First seen · 219 lines · 90 tokens per session scan A 61f30ab4165d
temps-add-handler is a skill published in the GitHub repository gotempsh/temps (903 stars, last pushed yesterday), licensed Apache-2.0. It adds 90 tokens to every session and 2,713 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-02.
temps-add-handler compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| temps-add-handlergotempsh/temps | Skill | 903 | yesterday | Apache-2.0 | A | 90 | Claude Code, Codex |
| bunjs-productionMadAppGang/claude-code | Skill | 287 | 7mo ago | MIT | A | 52 | Claude Code |
| reviewing-blogsappwrite/appwrite | Skill | 58k | yesterday | BSD-3-Clause | A | 55 | Cursor |
| java-modernpiomin/claude-ai-spring-boot | Skill | 1.4k | 7d ago | Apache-2.0 | A | 46 | Claude Code |
| claude-apiPrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 193 | Claude Code, Codex |
| release-preflightPrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 76 | Claude Code |
| release-db-config-syncPrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 91 | Claude Code |