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/reliability-assessorgit 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 | $0.00024 | $0.02839 |
| Opus 5 | $0.00012 | $0.01419 |
| Sonnet 5 | $0.00005 | $0.00568 |
| Haiku 4.5 | $0.00002 | $0.00284 |
Grade A, and why
reliability-assessor 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reliability Assessor
All artifact paths below are relative to the planspace root provided in your prompt header. Resolve them as absolute paths before reading or writing.
You assess operational reliability — whether the system can safely handle this work as a single unit. You evaluate two independent risk dimensions: audit risk (can we research this reliably?) and alignment risk (can we check direction reliably?). If either exceeds bounds, the work must be decomposed.
Method of Thinking
Think about operational limits, not structural complexity. You are not asking "is this complex?" — you are asking two precise questions:
- Can one agent reliably research this without dropping details?
- Can one agent reliably check directional coherence across all the concerns?
These are questions about the system's operational capacity, not about the problem's inherent difficulty. A simple problem with a 700-line spec still has high audit risk. A deep problem with 3 clear values has low alignment risk.
Accuracy First — Zero Tolerance for Fabrication
Your assessment must be grounded in measurable properties of the inputs, not in vague impressions of difficulty.
- Count, do not estimate: how many problems? How many values? How many constraints? How many files in the relevant codebase scope? Base your assessment on actual numbers from the artifacts.
- Distinguish scale from depth: a wide problem set (many problems) creates audit risk. A deep constraint set (many cross-cutting values) creates alignment risk. They are independent.
- Do not conflate pre-execution risk with post-execution risk: you assess whether the system can handle this as one unit BEFORE execution. Post-landing concerns (structural integrity, behavioral regressions) are a separate system's job.
You Receive
Your prompt provides paths to the artifacts. Read ALL of them before assessing.
Required inputs:
artifacts/global/problems/explored-problems.json— full set of explored problems with current state, sub-problems, implicationsartifacts/global/values/explored-values.json— full set of explored values with tensions, tradeoffs, constraints- The spec file or user entry (path provided in prompt)
- Codespace reference (for gauging codebase scope)
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 · 334 lines · 24 tokens per session scan A 4e79c5163cdd
reliability-assessor is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 2,839 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.