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 skills add alphabravo-oss/guild --skill tracegit clone --depth 1 https://github.com/alphabravo-oss/guildWrote 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/alphabravo-oss/guild/trace)<a href="https://agentmods.dev/skills/alphabravo-oss/guild/trace"><img src="https://agentmods.dev/badge/skills/alphabravo-oss/guild/trace/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/alphabravo-oss/guild/trace"><img src="https://agentmods.dev/badge/skills/alphabravo-oss/guild/trace.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 | $0.00040 | $0.06868 |
| Opus 5.5 | $0.00016 | $0.02747 |
| Sonnet 5.5 | $0.00008 | $0.01374 |
| Haiku 4.5 | $0.00004 | $0.00687 |
Grade A, and why
trace 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 1mo 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 — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundry integration: This skill's Q1–Q5 methodology is used in Foundry's F2 TRACE stream, enhanced with Serena LSP for deterministic symbol resolution. The
traceragent (agents/tracer.md) is the agent-runtime wrapper around this skill.
/foundry:trace — Spec-Anchored Code Completeness Audit
Trace every function and data flow against the original spec. Verify end-to-end wiring — not just that code exists, but that it's connected and does real work.
Tests and builds do NOT count as quality gates. Code that compiles and passes tests can still have disconnected functions, missing API calls, and incomplete data flows. The Logical Audit catches what tests miss.
Mindset: Assume the Code is Broken
Your job is to FIND what's wrong, not confirm the code works. Assume every function has a bug until you prove otherwise by reading the body. If you finish with zero findings, you failed — go back and look harder.
Task
Step 0: ANCHOR — Load the Spec and Observable Truths
- Load the spec — file path or inline text
- Extract all user stories (US-N) with acceptance criteria
- Extract all functional requirements (FR-N) and technical design
- Build a checklist of every verifiable requirement
- Load observable truths — if casting files or spec sections have
--- OBSERVABLE TRUTHS ---blocks, read them. Each OT-N becomes a verification target. Observable truths are often MORE specific than spec requirements and catch THIN implementations that technically satisfy the spec but miss the intent. - Store the spec reference for re-reading in subsequent verification iterations
Step 0.5: WIDTH — read the scope the run recorded
The checklist is what the spec says. What you must WALK this cycle is what the run recorded — you read the width, you never decide it. Call Foundry-Next and read inspect_mode out of the RESPONSE, not out of the display:
inspect_mode.mode—FULLorDELTA, decided by theFoundry-Phasetransition that opened this INSPECT. Nothing you do changes it andFoundry-Nextonly reports it.inspect_mode.stream_scope.trace.scope—full,deltaorskippedfor YOUR stream; itsdetailnames by how much the walk was narrowed. A cycle recordedDELTAwhose TRACE scope isfullis still a full walk for you.inspect_mode.touched_files— the repo-relative files the GRIND commits touched, measured at the boundary frominspect_mode.diff_base. This is the TRACE roster on aDELTAcycle.inspect_mode.cycle— the cycle that scope belongs to. A scope stamped with a different cycle is not yours; walk everything.
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.
- 1mo ago Changed · +74 lines 9d44bdc1b0d9
- 1mo ago First seen · 356 lines · 40 tokens per session scan A 9f2605bb5f97
trace is a skill published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 11d ago), licensed MIT. It adds 40 tokens to every session and 6,868 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart. Do not use for ordinary review, style feedback, or general improvement suggestions.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.