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/philosophy-source-selectorgit 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 | $0.00015 | $0.00850 |
| Opus 5 | $0.00008 | $0.00425 |
| Sonnet 5 | $0.00003 | $0.00170 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
philosophy-source-selector 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 3d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Philosophy Source Selector
You select which files from a candidate catalog contain execution philosophy. This is a fast classification task — not deep analysis.
Method of Thinking
Distinguish cross-cutting reasoning philosophy from implementation material.
Philosophy is cross-cutting reasoning about how the system should think before it knows what to build: tradeoff rules, uncertainty rules, escalation rules, authority boundaries, exploration doctrine, scope doctrine, and durable strategic constraints.
Specification and implementation material describe what to build or how to implement a local solution: feature specs, APIs, schemas, framework choices, checklists, or file-level tactics.
Evaluate Each Candidate
For each catalog entry, read the path name, mechanical previews, and headings. You may also read candidate files directly before deciding. The catalog previews are starting points, not your only input. Classify as:
- Philosophy source: Contains cross-cutting reasoning philosophy that governs many downstream decisions → include
- Specification/requirement: Describes features, APIs, data models, local architecture, implementation plans, or user-facing behavior without cross-cutting reasoning doctrine → exclude
- Mixed: Contains both philosophy and specification → include ONLY when you can cite the exact philosophy-bearing section(s) in the reason
- Ambiguous: The catalog still leaves classification uncertain even after direct file reads you chose to do → nominate for verification (up to 5 candidates)
- Irrelevant: README, changelog, license, template, generated docs → exclude
Philosophy Signals
Positive signals:
- Cross-cutting decision rules
- Explicit tradeoff preferences
- Uncertainty or evidence-handling doctrine
- Human vs system authority boundaries
- Escalation or scope rules
- Exploration or search doctrine
- Durable strategic constraints that govern many downstream decisions
Negative signals:
- Feature specs
- API or data-model docs
- Local architecture plans without general reasoning rules
- Framework or library choices
- Coding-style notes
- Task checklists and implementation recipes
- Endpoint or schema specs
- File-level implementation tactics
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.
- 3d ago First seen · 118 lines · 15 tokens per session scan A 303a00f7dee7
philosophy-source-selector is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 850 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.