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 instructions/adham90/opentrace/claude-mdgit clone --depth 1 https://github.com/adham90/opentraceWrote 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/instructions/adham90/opentrace/claude-md)<a href="https://agentmods.dev/instructions/adham90/opentrace/claude-md"><img src="https://agentmods.dev/badge/instructions/adham90/opentrace/claude-md.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 | $0.00953 | $0.00953 |
| Opus 5 | $0.00477 | $0.00477 |
| Sonnet 5 | $0.00191 | $0.00191 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
opentrace CLAUDE.md 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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Build & Test
go build -o opentrace ./cmd/opentrace
go test -short -race ./... # unit tests (no Docker)
go test -race ./... # full suite (needs Docker)
go vet ./... # linting
go mod tidy # after adding new imports
Do
- Use
store.ErrNotFoundsentinel for 404 responses - Use
server.WriteJSON(w, status, data)/server.WriteError(w, status, msg)for HTTP responses - Use
log/slogwith structured key-value fields — always include"error"key on errors - Guard integration tests with
testing.Short()skip - Use
?placeholders in SQLite queries — never string interpolation - Store booleans as INTEGER 0/1, timestamps as RFC3339 TEXT, UUIDs as TEXT
- Cast MCP tool args from
float64(JSON default) before using asint - When adding a store interface method, update ALL mock implementations (
internal/testutil/mocks/,internal/api/mock_test.go, and any package-local test doubles —grepthe method name) - When adding a new store, add to
pkg/store/(interface + model) andinternal/adapter/sqlite/(implementation, wired ininternal/adapter/sqlite/stores.go) - Use the
server.Modulepattern for new HTTP features — seeinternal/routes/<name>/module.gofor examples - Run
go mod tidyafter adding new imports - Cap all pagination
limitparams to a reasonable maximum (100-500) - Validate and sanitize all user input at handler boundaries
Don't
- Don't use
fmt.Printlnor the oldlogpackage — useslog.*only - Don't shadow an imported package name with a local variable (e.g. a local
watcherin a file that importsinternal/watcher) - Don't use CGO — all dependencies must be pure Go for cross-compilation
- Don't leak internal error details (SQL, file paths, stack traces) in HTTP responses
- Don't add store fields directly to
server.Deps— embed them instore.Storesinstead - Don't skip
testing.Short()guards on tests that need Docker or network - Don't hardcode magic numbers — use named constants
- Don't write functions longer than ~100 lines — extract helpers
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.
- 5d ago First seen · 66 lines · 953 tokens per session scan A fb06fc2f886a
opentrace CLAUDE.md is an instructions file published in the GitHub repository adham90/opentrace (15 stars, last pushed 3d ago), licensed MIT. It adds 953 tokens to every session, about $0.0048 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 instructions, from other repositories
opensre AGENTS.md
AGENTS.md instructions for Tracer-Cloud/opensre, covering opensre development reference, ci failures and tests (mandatory — every pr / push), build and run commands, code style and tests (high-signal, not exhaustive).
Exceptionless AGENTS.md
AGENTS.md instructions for exceptionless/Exceptionless, covering exceptionless, start here, common commands, project map and frontend direction.
evlog AGENTS.md
AGENTS.md instructions for HugoRCD/evlog, covering evlog, commands, monorepo structure, conventions and code style: no slop.
tslog AGENTS.md
AGENTS.md instructions for fullstack-build/tslog, covering project overview, settings are grouped (v5), quick reference, build system and build configs.
opensre CLAUDE.md
Claude Code instructions for Tracer-Cloud/opensre, a project described as: Build your own AI SRE agents. The open source toolkit for the AI era.
fess CLAUDE.md
Claude Code instructions for codelibs/fess, covering claude.md, project overview, tech stack, development commands and setup.