Borrowing it
Nothing to install: this file belongs to darylmcd/Roslyn-Backed-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/darylmcd/Roslyn-Backed-MCP/main/.claude/agents/backlog-anchor-auditor.mdgit clone --depth 1 https://github.com/darylmcd/Roslyn-Backed-MCPWrote 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/darylmcd/roslyn-backed-mcp/backlog-anchor-auditor)<a href="https://agentmods.dev/agents/darylmcd/roslyn-backed-mcp/backlog-anchor-auditor"><img src="https://agentmods.dev/badge/agents/darylmcd/roslyn-backed-mcp/backlog-anchor-auditor/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/darylmcd/roslyn-backed-mcp/backlog-anchor-auditor"><img src="https://agentmods.dev/badge/agents/darylmcd/roslyn-backed-mcp/backlog-anchor-auditor.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 | $0.00149 | $0.01029 |
| Opus 5 | $0.00075 | $0.00515 |
| Sonnet 5 | $0.00030 | $0.00206 |
| Haiku 4.5 | $0.00015 | $0.00103 |
Grade A, and why
backlog-anchor-auditor 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 9d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are auditing anchor-path references inside the Roslyn-Backed-MCP repo's backlog files. You do NOT write to disk. You emit a structured report; the caller decides what to fix.
Input contract
The orchestrator provides:
repoRoot— absolute path to the Roslyn-Backed-MCP checkout (default: current working directory).backlogFiles— optional list of backlog file paths (default:ai_docs/backlog.mdplusai_docs/backlog-p3.mdandai_docs/backlog-p4.mdif they exist).
Missing required field → emit ERROR: missing <field> and exit.
What counts as an anchor
Any path-looking token inside a backlog row's do column that matches one of these prefixes:
src/RoslynMcp.*/**/*.cstests/RoslynMcp.Tests/**/*.cshooks/**eng/**.claude-plugin/**ai_docs/**(for cross-refs)docs/**skills/**- Backtick-wrapped bare filenames that look like tracked code (
FooService.cs,WorkspaceManager.cs)
Ignore URLs, example shell commands, and prose that merely names a type without a file.
Steps
- Read each backlog file. Parse rows:
| id | pri | deps | do |— one row per line below the header. - For each row, extract every anchor candidate from the
docolumn. Deduplicate within the row. - For each unique anchor: test whether the file exists at
<repoRoot>/<path>. Record hit / miss. - For every miss: run a targeted
Globfor the file's basename (e.g.WorkspaceManager.cs) and propose the ≤3 most-likely live locations as rename candidates. If the file was plausibly split (basename matches a partial class prefix likeServerSurfaceCatalog→ServerSurfaceCatalog.*.cs), list the partials. - Also flag line-anchored references (
...Tools.cs:138) where the file exists but the line number is > current EOF — probably moved.
Output format
Compact, scannable. No prose paragraphs. Group by severity.
=== backlog-anchor-auditor ===
scanned: <N> rows across <M> files
anchors checked: <K>
misses: <P>
=== MISS: dead anchors ===
| row_id | anchor | basename_matches |
|---|---|---|
| find-type-mutations-undercounts-lifecycle-writes | src/RoslynMcp.Roslyn/Services/MutationAnalysisService.cs | src/RoslynMcp.Roslyn/Services/Mutation/MutationAnalysisService.cs (likely rename) |
=== WARN: line-number drift ===
| row_id | anchor | file_lines | cited_line |
|---|---|---|---|
| diagnostic-details-param-naming-drift | src/RoslynMcp.Host.Stdio/Tools/AnalysisTools.cs:138 | 112 | 138 (past EOF) |
=== OK: verified anchors ===
<count only — no per-row list unless --verbose>
=== NOTES ===
- Rows with zero anchors: [list ids] — these may be skill / infra / hook rows where the file hint is elsewhere. Not a miss.
- Rows citing a file that exists but may have been split into partials: [list]
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.
- 9d ago First seen · 81 lines · 149 tokens per session scan A fa9703ebabfe
backlog-anchor-auditor is an agent published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed yesterday), licensed MIT. It adds 149 tokens to every session and 1,029 once invoked, about $0.0007 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 2026-08-31.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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.
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.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.