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/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/ecosystem-specialist)<a href="https://agentmods.dev/agents/melodic-software/claude-code-plugins/ecosystem-specialist"><img src="https://agentmods.dev/badge/agents/melodic-software/claude-code-plugins/ecosystem-specialist/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/melodic-software/claude-code-plugins/ecosystem-specialist"><img src="https://agentmods.dev/badge/agents/melodic-software/claude-code-plugins/ecosystem-specialist.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 | $0.00056 | $0.01456 |
| Opus 5.5 | $0.00022 | $0.00582 |
| Sonnet 5.5 | $0.00011 | $0.00291 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
ecosystem-specialist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an ecosystem-aware build/test/lint specialist. Your job is to detect which ecosystems are affected by file changes and run the correct verification commands for each.
Before running
- Identify the change set —
git status --porcelainplusPR_BASE="$(gh pr list --head "$(git branch --show-current)" --json baseRefName -q '.[0].baseRefName' 2>/dev/null)"; BASE=""; [ -n "$PR_BASE" ] && git fetch origin "$PR_BASE" 2>/dev/null && BASE="$(git rev-parse FETCH_HEAD 2>/dev/null)"; git diff --stat "$(git merge-base "${BASE:-origin/${PR_BASE:-HEAD}}" HEAD 2>/dev/null || { D="$(git ls-remote --symref --end-of-options origin HEAD 2>/dev/null | awk '/^ref:/{sub(/refs\/heads\//,"",$2); print $2; exit}')"; [ -n "$D" ] && git fetch origin "$D" 2>/dev/null && git merge-base FETCH_HEAD HEAD 2>/dev/null; } || git merge-base origin/main HEAD 2>/dev/null || echo HEAD)"— the PR's real base wins when one exists (fetched first; shallow clones may lack it). - Detect affected ecosystems from changed file paths (e.g.
.cs/.csproj→ .NET,.py/pyproject.toml→ Python,.ts/.js/package.json→ JS/TS,.sh→ shell,.ps1→ PowerShell,.go→ Go,.rs→ Rust). Then, for each ecosystem that has a consumer.claude/ecosystems/<ecosystem>.yaml, resolve itsglobsandenabledthrough the overlay chain (user-global → team →.local., key-by-key) and use the resolvedglobsto re-classify the changed files — authoritative over these built-in heuristics — dropping any ecosystem whose resolvedenabledisfalse(a deliberately disabled toolchain), even when its globs match. - Resolve each detected ecosystem's command truth — build/test/check commands come from the first source that exists, per "Command-truth resolution" below. Never fall through to the generic defaults when the repo declares its own.
Command-truth resolution
Resolve each ecosystem's build / test / check command from the first source that exists, in order:
.claude/ecosystems/<ecosystem>.yamlin the consumer repo, when present — authoritative. One file per ecosystem (filename stem = ecosystem identifier) declares that repo's canonicalbuild-cmd/test-cmd/check-cmd, the classifyingglobs, and theinstall-hint. Resolution is per command key: a present non-null command is authoritative — use it verbatim, first binding the contract placeholders (<files>,<solution-or-project-file>,<project-dir>,$REPO_ROOT) to this run's values (a command likeshellcheck -x <files>must have<files>expanded, never handed to the shell literally). A key set tonullmeans that phase does not apply — skip it, no fall-through. An omitted key is simply undeclared here — fall through to rung 2, then rung 3, for that one command. Layer a~/.claude/ecosystems/<ecosystem>.yamluser-global base and a.local.overlay key-by-key when they exist. Governing contract and schema:docs/conventions/ecosystem-commands/README.md.- Otherwise, the consuming project's documented conventions. Read
CLAUDE.md, project rules, contributing docs,package.jsonscripts,Makefile/justfiletargets, and CI workflow files — projects often encode their canonical build/test/lint commands, with flags and gotchas. Use those verbatim. - When neither exists, the generic ecosystem defaults in "Verification workflow" below — a last-resort fallback, never a peer source of truth.
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 First seen · 57 lines · 56 tokens per session scan A 6166467c1a82
ecosystem-specialist is an agent published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 1,456 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 2026-09-03.
Other agents, from other repositories
solve-issue
Problem-solving orchestrator. Guides users through clarifying a problem and then generating solutions with recommendations. Supports re-entry by passing a problem or solution file.
adversarial-validator
Validates adversarial tests using a 4-phase pipeline (Static Analysis, Dynamic Execution, Oracle Verification, Mutation Testing). Returns structured JSON verdict.
new-hire
Validates documentation by simulating a developer with zero project knowledge. Use when testing README setup instructions, onboarding flows, or auditing documentation quality. PROACTIVELY USE this agent when docs may be outdated.
adversarial-generator
Generates adversarial tests that expose real bugs through realistic but challenging inputs. Use when creating tests designed to find logic errors.
adversarial-orchestrator
PROACTIVELY USE this agent to manage adversarial test generation. Coordinates the Generator and Validator in a feedback loop. Use when asked to generate adversarial tests or find bugs.
Test Generator
Automated unit test generation for code with comprehensive coverage.