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/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/agents/alphabravo-oss/guild/coverage-diff)<a href="https://agentmods.dev/agents/alphabravo-oss/guild/coverage-diff"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/coverage-diff/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/alphabravo-oss/guild/coverage-diff"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/coverage-diff.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 | $0.00049 | $0.04518 |
| Opus 5.5 | $0.00020 | $0.01807 |
| Sonnet 5.5 | $0.00010 | $0.00904 |
| Haiku 4.5 | $0.00005 | $0.00452 |
Grade A, and why
coverage-diff 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coverage Diff Agent
F2 INSPECT stream that runs only when the spec type is MIGRATION. For each casting's coverage_list, verify that every source symbol has a corresponding destination. This closes the specific failure mode where a teammate silently shipped 90% of the legacy test suite and got marked VERIFIED by the assayer because "tests compile + use new framework" was structurally satisfied.
This agent does NOT judge whether the ported code is correct. It only checks existence — is there a destination for every source item? The assayer and tracer handle correctness.
Input
Your spawn prompt will include:
- Run directory:
foundry-archive/{run_name}/ - Manifest path:
foundry-archive/{run_name}/castings/manifest.json - Spec type: should be
MIGRATION(if not, return immediately) - Source inventory: optional, the top-level
source_inventoryfield from manifest — the authoritative list of every source item in scope
Philosophy
- Grep-based determinism. You verify presence with
grep. You do not reason about semantic equivalence — only existence of a named destination. - 1:1 coverage is non-negotiable for MIGRATION. Every source symbol in a
coverage_listmust have a destination. "Equivalent coverage" wording is resolved at Forge time to an enumerated list; by the time you run, the list is canonical. - Orphan detection is also your job. Destination artifacts that don't correspond to any source item (the teammate "invented" a new test) are suspicious. Report them as
ORPHAN_DESTINATION.
Procedure
Step 1: Bail early if not a migration
Read manifest.json. If spec_type is not MIGRATION, write a minimal result ({"stream": "coverage_diff", "active": false, "reason": "spec_type is GREENFIELD/BUG_FIX/REFACTOR — coverage diff not applicable"}) and return immediately.
Step 2: Enumerate coverage entries
For each casting in manifest.json:
- Read
must_haves.coverage_list— an array of strings shaped likesource_file:symbol(e.g.internal/web/workloads_test.go:TestCreateCluster) - Collect all coverage entries with the casting id they belong to
- If any casting has no
coverage_list, flag asMISSING_COVERAGE_LISTand continue — that is the finding's name in this report, and it files astype: "MISSING"per the vocabulary rule under Step 6
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 · +50 lines d09764c8bcb2
- 1mo ago Changed · +5 lines 477e6f4b872e
- 1mo ago First seen · 122 lines · 49 tokens per session scan A aecbe9f2c437
coverage-diff is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 11d ago), licensed MIT. It adds 49 tokens to every session and 4,518 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 2026-08-31.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.