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 skills/chrisgagne/grounded-forge/gridmaker-interviewnpx skills add chrisgagne/grounded-forge --skill gridmaker-interviewgit clone --depth 1 https://github.com/chrisgagne/grounded-forgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chrisgagne/grounded-forge/gridmaker-interview)<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/gridmaker-interview"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/gridmaker-interview.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00127 | $0.06566 |
| Opus 5 | $0.00063 | $0.03283 |
| Sonnet 5 | $0.00025 | $0.01313 |
| Haiku 4.5 | $0.00013 | $0.00657 |
Grade A, and why
gridmaker-interview 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 4d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gridmaker Interview
Single-process dialogue skill. One operator per session, no subagents. Produces one self-lens spec.
A self-lens is a named-real-person lens (see creating-lenses Phase 1, branch (a)) where the named person is the operator running the skill. The same six-section lens spec, the same grounding-contract discipline, the same ventriloquism guard — with the as-if clause sharpened: reads as if {operator}-at-time-T were reading, given the material this interview surfaces; it is not {operator}-now, and {operator}-now is the seer choosing to look through it.
The fifteen-question protocol draws on several research traditions, each shaping one aspect of the interview:
- Christensen, Hall, Dillon & Duncan (Competing Against Luck, HarperBusiness, 2016) — the jobs-to-be-done framework, which asks what is the operator hiring this tool to do for them? Shapes the opening question about the trigger moment.
- Rogers (Client-Centered Therapy, Houghton Mifflin, 1951) — non-directive warmth: reflect what you heard before pushing for more. Shapes the overall register.
- The Adult Attachment Interview's adjective-and-memory technique (George, Kaplan & Main, 1985/1996) — ask for an adjective, then ask for a specific memory behind it; the gap between the two is the signal. Shapes Q8. Borrowed as a self-elicitation aid, not as the AAI's clinical instrument: the AAI is an attachment-classification protocol requiring trained coders, a full transcript, and the Main-Goldwyn / Hesse coding manual, none of which apply here.
- McAdams (The Life Story Interview, Northwestern, 2007) — high-point and low-point scenes; the pattern in how the operator tells the low point (it became useful, or it still costs) matters more than the story. Shapes Qs 9 and 10.
- Aron et al. (Personality and Social Psychology Bulletin 23(4), 1997) — a conversation gradient where questions get steadily more personal, then ease back. Shapes the running order: present circumstance first, deeper material in the middle, lighter close.
- Kegan (In Over Our Heads, Harvard, 1994) — the developmental move of taking assumptions you stand inside and holding them up to look at. Shapes the optional reserve question and Q14's values prompt.
- Heath & Heath (Switch, 2010) and adjacent identity-shift literature — the framing underneath the closing question's second half ("…and whether that's who you want to be becoming"). Cite as allusion, do not lift phrasing.
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.
- 4d ago First seen · 217 lines · 0 tokens per session scan A a1dc1cac4823
gridmaker-interview is a skill published in the GitHub repository chrisgagne/grounded-forge (7 stars, last pushed 13d ago), licensed MIT. It adds 127 tokens to every session and 6,566 once invoked, about $0.0006 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 skills, from other repositories
warpp-workflow-authoring
Author WARPP workflows for Manifold as typed-port dataflow JSON. Use when a user asks to build, create, design, generate, or edit a Flow / workflow / automation / pipeline / DAG in Manifold, or mentions WARPP, workflow nodes, or the /flow builder. Covers the document format, port types and coercions, the builtin node…
manifold-api
Use when an agent needs to inspect or call the local Manifold HTTP API. Provides guidelines and scripts to filter specs before reading and handle payloads safely.
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.