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 byteseek/Mira --skill sec-filing-analysisgit clone --depth 1 https://github.com/byteseek/MiraWrote 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/byteseek/mira/sec-filing-analysis)<a href="https://agentmods.dev/skills/byteseek/mira/sec-filing-analysis"><img src="https://agentmods.dev/badge/skills/byteseek/mira/sec-filing-analysis/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/byteseek/mira/sec-filing-analysis"><img src="https://agentmods.dev/badge/skills/byteseek/mira/sec-filing-analysis.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 Excessive Agency · line 210 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00031 | $0.01795 |
| Opus 5 | $0.00015 | $0.00898 |
| Sonnet 5 | $0.00006 | $0.00359 |
| Haiku 4.5 | $0.00003 | $0.00179 |
Grade A, and why
sec-filing-analysis 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 11d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEC Filing Analysis Skill
This skill is used when Mira needs to analyze SEC disclosure itself, not merely cite SEC as a source.
It supports two routes:
sec_supplement: lightweight SEC fact verification inside another research workflow.sec_filing_deep_dive: dedicated analysis of a filing such as 10-K, 10-Q, S-1, 8-K exhibit, DEF 14A, 13F, or Form 4.
Route Selection
Use sec_supplement when:
- the primary task is single-equity research, earnings analysis, monitoring, event delta, or portfolio review
- SEC data is needed to verify a fact, metric, filing timeline, share count, cash flow item, debt item, SBC, inventory, RPO/backlog, segment value, risk factor, or governance detail
- the output should update the active case evidence log, financial snapshot, or case notes
Use sec_filing_deep_dive when:
- the user explicitly asks to analyze a filing, annual report, quarterly report, S-1, proxy, 8-K exhibit, 13F, Form 4, or similar document
- a thesis depends on filing-level details that cannot be answered by a quick metric lookup
- a company release, management commentary, market-data page, or prior case conflicts with the filing
- accounting quality, risk-factor delta, related-party transactions, debt/liquidity, customer concentration, segment disclosure, ownership/control, dilution, or non-GAAP reconciliation is central to the conclusion
If a filing is not yet available, do not fabricate filing analysis. Write a source-gap refresh item and state what the later filing must verify.
SEC Authority Rules
- A specific issuer filing from SEC Archives, company IR, or filed exhibit can support
issuer_primary_disclosureclaims. - SEC
submissionsmetadata andcompanyfactsJSON are official regulatory data sources, but record them as the registry/source-class authority defines unless the case has a specific reason to classify the extracted claim differently. - Companyfacts rows must record CIK, taxonomy, tag, unit, fiscal period, form, filed date, frame if available, and as-of date.
- Filing rows must record CIK, accession number, form type, filing date, report period, source URL, and section or exhibit when relevant.
- Do not treat an XBRL tag name as self-explanatory. If the tag is non-standard or company-specific, state the label/context and downgrade comparability.
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.
- 11d ago First seen · 229 lines · 31 tokens per session scan A a0b726d6ec26
sec-filing-analysis is a skill published in the GitHub repository byteseek/Mira (268 stars, last pushed 3d ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,795 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 2026-08-30.
Other skills, from other repositories
cost
Deep cost exploration and transparency. Shows real token usage, session costs, campaign spend, burn rates, and model breakdown. Reads Claude Code's native session data for exact numbers. Complements /dashboard with focused cost views.
creating-financial-models
A financial analysis toolkit for valuing companies, projects, or acquisitions and testing how assumptions affect the results.
aml_screening
Screen transactions for money laundering patterns and risk indicators.
get_financial_statements
Get financial statements (income, balance, cash flow) for a company.
analyze_risk_metrics
Calculate risk metrics (VaR, Sharpe, volatility) given a set of returns.
fetch_economic_indicators
Fetch economic indicators like GDP, CPI, Unemployment.