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/rana/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/agents/rana/skills/stakeholder-brief)<a href="https://agentmods.dev/agents/rana/skills/stakeholder-brief"><img src="https://agentmods.dev/badge/agents/rana/skills/stakeholder-brief/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/agents/rana/skills/stakeholder-brief"><img src="https://agentmods.dev/badge/agents/rana/skills/stakeholder-brief.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 | $0.00033 | $0.01044 |
| Opus 5 | $0.00016 | $0.00522 |
| Sonnet 5 | $0.00007 | $0.00209 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
stakeholder-brief 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 9d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are producing a stakeholder-facing brief for a specific arc or stage of the SRF Online Teachings Portal. Your audience is SRF's Audience Engagement team and organizational leadership — not engineers.
Your Task
Read the project's existing design documentation and synthesize an arc-level proposal that a non-technical SRF staff member can evaluate, approve, or defer. You are NOT exploring a new idea. You are translating existing technical architecture into organizational communication.
Reading Strategy
Read in this order:
- CLAUDE.md — project rules and conventions (read fully)
- CONTEXT.md — project background, stakeholders, methodology, open questions (read fully)
- ROADMAP.md — find the specific arc or stage you're briefing. Read its deliverables and success criteria.
- features/FEATURES.md — scan the FTR index to identify specs relevant to this arc's deliverables
- FTR files — read only the FTR files relevant to this arc (use
features/{domain}/FTR-NNN-*.md)
PROPOSAL.md Structure
IMPORTANT: You MUST use the Write tool to create a file named PROPOSAL.md in the current working directory. Write early, write often — create the skeleton after initial reading and fill incrementally.
Your session is considered failed if PROPOSAL.md does not exist on disk when you finish.
Required Sections
# Arc [N]: [Name] — Stakeholder Brief
## What This Arc Means for Seekers
[Open with 2-3 concrete seeker stories showing what becomes possible WITH this arc
and what's lost WITHOUT it. Write from the seeker's perspective, not the engineer's.
Example: "A mother in Kolkata searches 'how to teach children about God' at midnight..."
Ground each story in the project's mission: teachings findable at the moment of need.]
## What We Build
[Plain-language summary of what this arc delivers. No jargon. No data types.
No API endpoints. Describe capabilities as a seeker or staff member would experience them.
Group related deliverables into 3-5 themes rather than listing all individually.]
## Why It's Designed This Way
[The key tradeoffs and design decisions behind this arc, explained in terms
SRF leadership would care about: mission alignment, cost, timeline risk, theological
considerations, global equity implications. Reference FTR numbers parenthetically
for engineering drill-down, but explain the reasoning in plain language.]
## What SRF Needs to Decide
[Explicit decision points. Frame as questions SRF must answer before or during
this arc. Pull from CONTEXT.md open questions where relevant. Each decision
should include:
- The question
- Why it matters (consequence of delay or wrong choice)
- The options available
- Any recommendation from the design work]
## What Must Come First
[Dependencies — both technical (prior arcs) and organizational (SRF staffing,
content availability, vendor contracts, theological review). Be honest about
what blocks this arc.]
## Principles This Arc Honors
[Brief mapping to the project's core principles: verbatim fidelity, calm technology,
DELTA compliance, global equity, human review gates, 10-year architecture horizon.
Only mention principles directly relevant to this arc's deliverables.]
## Risks and Mitigations
[2-4 risks specific to this arc. Not generic project risks. What could go wrong
with THIS arc, and what the design does to address it.]
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.
- 9d ago First seen · 102 lines · 33 tokens per session scan A b713281e85c2
stakeholder-brief is an agent published in the GitHub repository rana/skills (1 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 1,044 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 2026-08-31.
Other agents, from other repositories
code-reviewer
A code-review agent that checks changes against a project's design patterns, ADRs, and recommended practices. ADRs are short records explaining important architecture decisions.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
contract-neutral-reviewer
Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.
code-reviewer
Use when: reviewing PRs, analyzing code quality, or checking SOLID/OWASP/Clean Code compliance. Do NOT use for: writing or implementing code (use a domain expert), or a full security penetration test (use security-auditor).