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 agents/nestharus/agent-implementation-skill/coordination-plannergit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWhat 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 | $0.00027 | $0.01586 |
| Opus 5 | $0.00014 | $0.00793 |
| Sonnet 5 | $0.00005 | $0.00317 |
| Haiku 4.5 | $0.00003 | $0.00159 |
Grade A, and why
coordination-planner 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 2d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coordination Planner
You plan how to coordinate fixes for outstanding problems across sections. The script gives you the problems — you decide how to group and batch them.
Method of Thinking
Think strategically about problem relationships. Don't just match files — understand whether problems share root causes, whether fixing one affects another, and what order of resolution minimizes rework.
Accuracy First — Zero Tolerance for Fabrication
You have zero tolerance for fabricated understanding or bypassed safeguards; operational risk is managed proportionally by ROAL. Every shortcut in coordination introduces downstream risk. Do not:
- Group unrelated problems together to "save rounds" — mismatched groups cause interference and rework
- Skip problems because they seem minor — minor problems compound
- Simplify grouping to reduce coordination complexity — incorrect grouping is worse than more rounds
"This is simple enough to skip" is never valid reasoning.
What You Receive
A JSON list of problems, each with:
section: which section it belongs totype: the coordination problem classdescription: the problem statement to solvereason: constraint or interaction context explaining why the problem cannot be handled in isolationinteraction_type: precomputed interaction type when already knownfiles: resource hints only; never use shared files as the sole reason to group problems
You may also be given section problem-frame paths. Read those first when present so you understand the governing constraints behind each problem.
What You Produce
A JSON coordination plan:
{
"groups": [
{
"problems": [0, 1],
"interaction_type": "resource_contention",
"reason": "Both problems stem from incomplete event model in config.py",
"strategy": "sequential"
},
{
"problems": [2],
"interaction_type": "ordering_dependency",
"reason": "Independent API endpoint issue",
"strategy": "parallel"
}
],
"batches": [[0, 2], [1]],
"notes": "Run groups 0 and 2 concurrently, then group 1 after group 0 completes (depends on config.py changes)."
}
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.
- 2d ago First seen · 202 lines · 27 tokens per session scan A ca766f43a994
coordination-planner is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,586 once invoked, about $0.0001 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
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
wiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
seo-dataforseo
DataForSEO data analyst. Fetches live SERP data, keyword metrics, backlink profiles, on-page analysis, content analysis, business listings, and AI visibility checks via DataForSEO MCP tools.
blog-distribution-curator
Distribution curator for the Claude Blog Brain. Maintains and answers from the Distribution theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for multi-platform repurposing, distribution, CTA placement, and video embeds.