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 skills add johnqtcg/awesome-skills --skill stock-analysis-leadgit clone --depth 1 https://github.com/johnqtcg/awesome-skillsWrote 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/johnqtcg/awesome-skills/stock-analysis-lead)<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/stock-analysis-lead"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/stock-analysis-lead/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/johnqtcg/awesome-skills/stock-analysis-lead"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/stock-analysis-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 356 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00229 | $0.11494 |
| Opus 5 | $0.00114 | $0.05747 |
| Sonnet 5 | $0.00046 | $0.02299 |
| Haiku 4.5 | $0.00023 | $0.01149 |
Grade A, and why
stock-analysis-lead 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 — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stock Analysis Lead — Orchestrator
Purpose
You are the orchestrator for a Multi-Agent US-equity research workflow. Your job is to:
- Identify the ticker and validate it is a US-listed equity
- Classify the company into a sector archetype (SaaS / Hyperscaler / Mature Cash Cow / Capital-Intensive / Cyclical / Financial / REIT / Payment Network) — this determines the threshold set for the Good-Company checklist and valuation norms, and is provisional until the workers can challenge it
- Fetch the standard data package (10-K, 10-Q, recent earnings call, current price, peer set, historical financials, earnings-revision momentum)
- Run the optionality test — it needs market cap, so it cannot run before step 3
- Triage: dispatch the Tier-0 core always, Tier-1 conditional workers only when their trigger fires
- Launch the wave in a single Agent batch; run the dispatch state machine (validate → retry once → timeout → quorum) over the replies
- Consolidate validated Findings and synthesize a provisional verdict using the "Good Company × Good Price" framework with an auditable probability-assignment procedure
- Only then read the prior verdict on this ticker and reconcile — reading it earlier anchors the whole analysis
- Append the verdict to the log (opt-in, portable path) so future analyses reckon with this one
Critical rule: You only fetch, triage, dispatch, and synthesize. You do NOT analyze fundamentals yourself — the workers do that. Drawing your own conclusions in parallel with the workers re-introduces the attention-dilution problem this architecture exists to solve.
Two things are never done by judgment: worker replies are accepted or rejected by scripts/finlib/worker_contract.py, and the run is publishable or not by scripts/finlib/runbundle.py. An orchestrator that eyeballs a worker's Markdown is the failure mode this version exists to remove.
Quick Reference
| Step | What | Section |
|---|---|---|
| 1 | Identify ticker; validate US listing | Step 1 |
| 1.5 | Select depth (Lite / Standard / Strict) | Step 1.5 |
| 1.5c | Classify sector archetype | Step 1.5c |
| 2 | Fetch the data package (incl. earnings revision) | Step 2 |
| 2b | Optionality test — needs market cap, so it runs after data | Step 2b |
| 3 | Triage: Tier-0 core + Tier-1 conditional | Step 3 |
| 4 | Dispatch in parallel; run the state machine | Step 4 |
| 5 | Synthesize provisional verdict | Step 5 |
| 5d-ter | Evidence gate — pre-verdict; blocks synthesis | Step 5d-ter |
| 5f-bis | Prior verdict review — deliberately AFTER the provisional verdict | Step 5f-bis |
| 5g | Publication gate — blocks the report + log append | Step 5g |
| — | Output format | Output Format |
| — | Consolidation rules | Consolidation Rules |
What ships with it
44 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.
- references/cognitive-bias-gates.md 16 KB
- references/data-acquisition-playbook.md 10 KB
- references/dispatch-protocol.md 20 KB
- references/earnings-revision-momentum.md 5.3 KB
- references/good-company-checklist.md 6.7 KB
- references/information-edge.md 6.7 KB
- references/output-format.md 6.8 KB
- references/scenario-framework.md 7.7 KB
- references/scenario-probability-calibration.md 13 KB
- references/sector-archetypes.md 21 KB
- references/valuation-methods.md 20 KB
- references/verdict-log-protocol.md 13 KB
- references/worker-contract.md 10 KB
- scripts/finlib/__init__.py 492 B runs code
- scripts/finlib/calibration.py 7.8 KB runs code
- scripts/finlib/crosssection.py 4.2 KB runs code
- scripts/finlib/dispatch.py 17 KB runs code
- scripts/finlib/edgar.py 7.3 KB runs code
- scripts/finlib/lint.py 11 KB runs code
- scripts/finlib/model.py 6.5 KB runs code
- scripts/finlib/ratios.py 8.4 KB runs code
- scripts/finlib/report_audit.py 7.1 KB runs code
- scripts/finlib/runbundle.py 26 KB runs code
- scripts/finlib/sotp.py 10 KB runs code
- scripts/finlib/valuation.py 11 KB runs code
- scripts/finlib/verdict_diff.py 2.8 KB runs code
- scripts/finlib/verdictlog.py 12 KB runs code
- scripts/finlib/worker_contract.py 18 KB runs code
- scripts/goldenrun.sh 4.4 KB runs code
- scripts/run_regression.sh 97 B runs code
- scripts/tests/test_dispatch.py 20 KB runs code
- scripts/tests/test_edge.py 3.1 KB runs code
- scripts/tests/test_finlib.py 9.2 KB runs code
- scripts/tests/test_goldenrun.py 10 KB runs code
- scripts/tests/test_model.py 8.5 KB runs code
- scripts/tests/test_orchestration_matrix.py 25 KB runs code
- scripts/tests/test_pipeline_e2e.py 21 KB runs code
- scripts/tests/test_report_audit.py 11 KB runs code
- scripts/tests/test_runbundle.py 51 KB runs code
- scripts/tests/test_skill_contract.py 15 KB runs code
- scripts/tests/test_skill_frontmatter.py 18 KB runs code
- scripts/tests/test_sotp.py 6.7 KB runs code
- scripts/tests/test_verdictlog.py 19 KB runs code
- scripts/tests/test_worker_contract.py 20 KB runs code
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 · 500 lines · 229 tokens per session scan A 810341df20b7
stock-analysis-lead is a skill published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed today), licensed MIT. It adds 229 tokens to every session and 11,494 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
cache-components
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). PROACTIVE ACTIVATION: Use this skill automatically when working in Next.js projects that have cacheComponents: true in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best…
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
blind-spot-pass
Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.