Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add equity-rigor/us-equity-research/plugin install us-equity-ic-rigorWrote 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/equity-rigor/us-equity-research/us-equity-ic-rigor)<a href="https://agentmods.dev/skills/equity-rigor/us-equity-research/us-equity-ic-rigor"><img src="https://agentmods.dev/badge/skills/equity-rigor/us-equity-research/us-equity-ic-rigor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/equity-rigor/us-equity-research/us-equity-ic-rigor"><img src="https://agentmods.dev/badge/skills/equity-rigor/us-equity-research/us-equity-ic-rigor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00703 | $0.13607 |
| Opus 5 | $0.00351 | $0.06803 |
| Sonnet 5 | $0.00141 | $0.02721 |
| Haiku 4.5 | $0.00070 | $0.01361 |
Grade A, and why
us-equity-ic-rigor 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 12d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL: Verifier Script Path Resolution
This plugin bundles its verifier scripts at ${CLAUDE_PLUGIN_ROOT}/scripts/ and JSON schemas at ${CLAUDE_PLUGIN_ROOT}/schemas/. All scripts/verify_*.py references in this SKILL resolve to that location.
Execution requirements (non-negotiable)
1. Use the explicit plugin-root path for every script invocation.
python ${CLAUDE_PLUGIN_ROOT}/scripts/verify_eps_pe.py --memo-json outputs/<TICKER>_structured.json
python ${CLAUDE_PLUGIN_ROOT}/scripts/verify_view_defensibility.py --memo-json outputs/<TICKER>_structured.json
If ${CLAUDE_PLUGIN_ROOT} is not set in the current Claude Code version, the plugin is installed at ~/.claude/plugins/<plugin-name>/<version>/ (e.g., ~/.claude/plugins/us-equity-ic-rigor/0.5.0/). Use that absolute path as a fallback.
2. NEVER fall back to "evaluate gates analytically."
If you cannot reach a verifier script for any reason (file not found, permission denied, Python import error, missing pydantic dependency, etc.), STOP execution of the current phase. Report the error to the user with the exact command attempted, the exact error message returned, and a request to either (a) clone the repo at https://github.com/equity-rigor/us-equity-research and run Claude Code from that directory, OR (b) manually copy the missing scripts to the plugin install location.
Do NOT proceed to produce a memo with gate statuses you judged yourself. Self-graded gates are not gates. They are LLM opinions about LLM output.
3. The verifier scripts are this framework's distinguishing feature. A memo produced without programmatic verification has no claim to the "20-gate verification" rigor advertised in the README. Self-graded gates produce a memo of the same quality as a careful prompt template — useful, but not what was promised.
4. Operator-explicit override (the only allowed degradation path). If the user explicitly says "I understand the verifiers won't run; proceed analytically anyway," THEN you may produce the memo with analytically-judged gate statuses. In that case you MUST set memo_metadata.gates_evaluated_analytically: true in <TICKER>_structured.json, include the disclaimer "Gate statuses in this memo were evaluated analytically by the language model; the programmatic verifier scripts did not execute for this output" in the IC memo header, set every gate's evaluation_method field to "analytical_llm", and cap the rubric score at 7.5 regardless of mechanical compliance.
What ships with it
40 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 2.1 KB
- commands/ic-memo.md 5.1 KB
- commands/red-team.md 5.2 KB
- references/bear-bridge-us.md 16 KB
- references/five-scenario-framework-us.md 14 KB
- references/gm-taxonomy-us.md 20 KB
- references/multi-audience-delivery-us.md 20 KB
- references/pm-redteam-rubric-us.md 19 KB
- references/position-sizing-us.md 16 KB
- references/quant-overlay-us.md 23 KB
- references/tail-risk-mapping-us.md 13 KB
- references/three-method-valuation-us.md 17 KB
- references/what-would-reverse-us.md 16 KB
- schemas/manifest.json 9.8 KB
- schemas/memo.json 43 KB
- schemas/scenarios.json 10 KB
- schemas/source_tags.json 18 KB
- schemas/verification_gates.json 15 KB
- scripts/verify_bank_metrics.py 11 KB runs code
- scripts/verify_bear_bridge.py 4.9 KB runs code
- scripts/verify_consensus_variance.py 12 KB runs code
- scripts/verify_eps_pe.py 6.0 KB runs code
- scripts/verify_fcf_definition.py 7.8 KB runs code
- scripts/verify_gm_taxonomy.py 3.9 KB runs code
- scripts/verify_headline_conditionality.py 11 KB runs code
- scripts/verify_non_gaap.py 8.7 KB runs code
- scripts/verify_provenance_manifest.py 12 KB runs code
- scripts/verify_quant_cross_doc_consistency.py 11 KB runs code
- scripts/verify_quant_overlay.py 12 KB runs code
- scripts/verify_revision_velocity.py 9.6 KB runs code
- scripts/verify_scenario_weights.py 5.0 KB runs code
- scripts/verify_segment_gm.py 6.8 KB runs code
- scripts/verify_sotp_monotonicity.py 12 KB runs code
- scripts/verify_source_tags.py 15 KB runs code
- scripts/verify_view_defensibility.py 25 KB runs code
- scripts/verify_weighting_sensitivity.py 4.9 KB runs code
- scripts/verify_what_would_reverse.py 4.8 KB runs code
- scripts/write_manifest.py 9.6 KB runs code
- templates/ic-debate-script-template-us.md 11 KB
- templates/opinion-letter-section-checklist-us.md 12 KB
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.
- 12d ago First seen · 304 lines · 0 tokens per session scan A 6b3f427d0b3c
us-equity-ic-rigor is a skill published in the GitHub repository equity-rigor/us-equity-research (4 stars, last pushed 1mo ago), licensed MIT. It adds 703 tokens to every session and 13,607 once invoked, about $0.0035 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.