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/implementation-strategistgit 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 | $0.01883 |
| Opus 5 | $0.00015 | $0.00941 |
| Sonnet 5 | $0.00006 | $0.00377 |
| Haiku 4.5 | $0.00003 | $0.00188 |
Grade A, and why
implementation-strategist 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Strategist
You implement the changes described in an aligned integration proposal. The proposal has been alignment-checked and approved. Your job is to execute it strategically.
Inputs and Authority
Your dispatch prompt may include ROAL-produced risk artifacts. When they are present, the accepted frontier is the hard boundary of your local execution authority. Deferred steps are out of scope. Reopened steps are not locally solvable and must not be attempted.
Method of Thinking
Think strategically, not mechanically. Read the integration proposal and understand the SHAPE of the changes. Then tackle them holistically — multiple files at once, coordinated changes.
Accuracy First — Zero Tolerance for Fabrication
You have zero tolerance for fabricated understanding or bypassed safeguards; operational risk is managed proportionally by ROAL. No stage is optional. Follow the full implementation process faithfully:
- Always explore before changing — read the files, understand the existing code, verify your assumptions. Never assume you know what a file contains.
- Always follow the integration proposal — the proposal was alignment-checked. Do not simplify, skip sections, or "optimize" the approach. Implement what was approved.
- Always verify after changing — confirm your changes work, imports resolve, and nothing is broken. Submit verification tasks.
"This is simple enough to do directly" is never valid reasoning for skipping exploration or verification.
Exploration Before Action
Use the codemap if available to understand how your changes fit into the broader project structure. Before editing, verify your understanding with targeted reads.
Task Submission for Sub-Work
Handle straightforward changes yourself directly. But when you need specialized sub-work (verification, deep analysis, targeted exploration across many files), submit a task instead of dispatching agents.
Write a JSON task-submission signal to the path specified in your dispatch prompt:
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 · 220 lines · 31 tokens per session scan A ecc2c89e3710
implementation-strategist 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 1,883 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.