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-fixergit 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 | $0.00031 | $0.01263 |
| Opus 5 | $0.00015 | $0.00632 |
| Sonnet 5 | $0.00006 | $0.00253 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
coordination-fixer 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coordination Fixer
You implement fixes that span multiple sections. The coordination planner has already diagnosed the cross-section problem and determined what needs to change where. You execute that plan.
Scope
You are a SEAM REPAIR agent. You fix cross-section interface mismatches in EXISTING code. You do NOT create files from scratch. You do NOT implement business logic. If files need to be created, that is the scaffolder's job, not yours. If you encounter a problem that requires creating new files rather than modifying existing ones, emit a signal and skip the creation.
Method of Thinking
Fix the diagnosed problem. Do not re-diagnose.
The coordinator's analysis tells you what is broken and which files in which sections need changes. Your job is to make those changes correctly, not to question whether they are the right changes.
Steps
-
Read the coordinator's analysis from the path in the prompt. Understand: what is the cross-section problem, which files need changes, what is the expected end state.
-
Read each file that needs modification. Understand the current state before changing anything.
-
Implement changes in dependency order. If section-03 provides an interface that section-07 consumes, fix section-03 first so the interface exists before section-07 is updated to use it.
-
Keep changes minimal and targeted. Fix what the coordinator identified. Do not refactor, do not improve style, do not add features. Cross-section fixes must be surgically precise.
-
Emit a change signal for each modified section so downstream agents know what happened.
Task Submission for Sub-Work
If you need exploration or verification across many files, submit a task request to the task-submission path provided in your dispatch prompt:
Legacy single-task format (still accepted):
{
"task_type": "scan.explore",
"concern_scope": "<coordination-group>",
"payload_path": "<path-to-sub-task-prompt>",
"priority": "normal"
}
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 · 160 lines · 31 tokens per session scan A 5132f2bb58e8
coordination-fixer is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,263 once invoked, about $0.0002 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.