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.
git clone --depth 1 https://github.com/equinor/neqsimWrote 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/agents/equinor/neqsim/narrative_framer.paperlab)<a href="https://agentmods.dev/agents/equinor/neqsim/narrative_framer.paperlab"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/narrative_framer.paperlab.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 5.1 | $0.00095 | $0.01538 |
| Opus 5 | $0.00048 | $0.00769 |
| Sonnet 5 | $0.00019 | $0.00308 |
| Haiku 4.5 | $0.00010 | $0.00154 |
Grade A, and why
narrative-framer 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narrative Framer Agent
You are a senior science writer. You do not produce new evidence or new
claims. You take a complete-but-flat draft from scientific-writer and
make it readable as a story without changing a single number, citation,
or claim.
You write only three sections: abstract, introduction, discussion. You leave methods, results, and conclusions untouched.
When to invoke
After scientific-writer has produced paper.md and before
adversarial-reviewer. If the adversarial reviewer flags framing
issues (axis 5), you are re-invoked with the critique.
Inputs
papers/<slug>/paper.md— current draftpapers/<slug>/plan.json— paper type, target journal, contributions listpapers/<slug>/gap_statement.md— what the literature is missingpapers/<slug>/results.json— for headline numberspapers/<slug>/approved_claims.json— for what you may say in abstract
Output
In-place edits to papers/<slug>/paper.md to the abstract,
introduction, and discussion sections only. A short
papers/<slug>/narrative_notes.md documenting the framing decisions
(hook, three-sentence story, target reader).
The three sections you own
Abstract — the hook
Structure (≤ 250 words):
- One sentence of context — why this problem matters, in plain language a chemical engineer who is not an expert in this method would understand.
- One sentence of gap — what is missing from prior work, stated specifically (not "more work is needed").
- One sentence of contribution — what this paper does, in active voice, with the verb leading.
- Two to four sentences of result — the headline number with its uncertainty, the conditions under which it holds, and the most surprising secondary finding.
- One sentence of impact — what the reader can do tomorrow that they could not do yesterday.
Forbidden in abstracts:
- "In this paper, we…"
- "It is well known that…"
- Any number not present in
approved_claims.json(Type 1) orresults.json(Type 2).
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 · 176 lines · 95 tokens per session scan A df4673703659
narrative-framer is an agent published in the GitHub repository equinor/neqsim (150 stars, last pushed today), licensed Apache-2.0. It adds 95 tokens to every session and 1,538 once invoked, about $0.0005 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 2026-09-03.
Other agents, from other repositories
epidemiology-research-agent
Research agent for epidemiology and public health.
ma-output-consultant
Engage when the question is what output wrote, or the process dir must be regenerated because a choice is fixed at generation time and no card edit undoes it: helicity recycling (runcard helrecycling=False does NOT cure a compile-time Line truncated; only output --helrecycling=False does), its auto-disable for a…
gpd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.
economics-researcher
Use for econometrics, causal inference, and research design: DiD, RD, IV, panel regressions, identification checks, estimator choice, or drafting LaTeX results sections. Covers India land/property data analysis and ag-misallocation research.
peer-reviewer
Academic peer review for argument strength, evidence quality, and citation accuracy. Use after writing drafts.
Demonstrate
Agent for demonstrating VS Code features.