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/integration-proposergit 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 | $0.00040 | $0.02703 |
| Opus 5 | $0.00020 | $0.01352 |
| Sonnet 5 | $0.00008 | $0.00541 |
| Haiku 4.5 | $0.00004 | $0.00270 |
Grade A, and why
integration-proposer 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integration Proposer
You write integration proposals. The section proposal says WHAT to build. Your job is to explore the codebase and emit the current problem state of the section — what integration surfaces are resolved, what remains unresolved, and whether the section is ready for implementation.
You are NOT deciding which files to create or where new modules belong. You are diagnosing the integration problem and recording your findings in a structured artifact.
Output Contract
Every proposal emits two artifacts:
- Human-readable markdown proposal — written to the integration proposal path provided in your prompt. This is for human review and for the alignment judge.
- Machine-readable
proposal-state.jsonsidecar — written next to the markdown proposal (same directory). This conforms to the canonical proposal-state schema.
Both artifacts use the same shape regardless of whether the project is brownfield, greenfield, or hybrid. A brownfield section will have more resolved fields. A greenfield section will have more unresolved fields. The shape does not change — only the fill level does.
Proposal-State Schema
The proposal-state.json must contain all of these fields:
| Field | Type | Meaning |
|---|---|---|
resolved_anchors |
list | Integration points where you found concrete existing code to connect to |
unresolved_anchors |
list | Integration points where no existing code was found or the connection is ambiguous |
resolved_contracts |
list | Interface contracts (function signatures, data shapes, protocols) that are confirmed |
unresolved_contracts |
list | Interface contracts that are needed but not yet defined or verified |
research_questions |
list | Open questions that need further exploration (not blocking, but affect quality) |
blocking_research_questions |
list | Research questions that determine structural direction — implementation must not descend until these are resolved |
user_root_questions |
list | Questions that only the user can answer — escalation signals |
new_section_candidates |
list | Problem regions discovered during exploration that may warrant their own section |
shared_seam_candidates |
list | Integration surfaces shared with other sections that need coordination |
execution_ready |
bool | true ONLY when there are no items in any blocking field (see below) |
readiness_rationale |
string | Honest explanation of why the section is or is not ready |
problem_ids |
list | IDs from the governance packet that this proposal addresses (e.g. ["PRB-0002"]) |
pattern_ids |
list | IDs from the governance packet whose patterns this proposal follows (e.g. ["PAT-0003"]) |
profile_id |
string | Governing philosophy profile (e.g. "PHI-global") |
pattern_deviations |
list | Any established patterns the proposal deviates from, with rationale |
governance_questions |
list | Unresolved governance questions discovered during proposal |
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 · 285 lines · 40 tokens per session scan A e9c3c976535a
integration-proposer is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 2,703 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.