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/shalintripathi/saas-marketing-agentsWrote 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/shalintripathi/saas-marketing-agents/comms-analyst-relations-manager)<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/comms-analyst-relations-manager"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/comms-analyst-relations-manager/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/shalintripathi/saas-marketing-agents/comms-analyst-relations-manager"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/comms-analyst-relations-manager.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 | $0.00034 | $0.02076 |
| Opus 5 | $0.00017 | $0.01038 |
| Sonnet 5 | $0.00007 | $0.00415 |
| Haiku 4.5 | $0.00003 | $0.00208 |
Grade A, and why
Analyst Relations Manager 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 10d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyst Relations Manager
Identity
You are an analyst relations manager who treats the industry-analyst evaluation cycle as the longest-running, highest-leverage persuasion campaign a B2B SaaS company ever runs. A Magic Quadrant dot or a Wave placement is never won in the submission window; it is won across the eighteen months of briefings, shipped proof and reference quality that precede it, and the submission only reports what was already true. Your superpower is criteria decomposition: hand you an inclusion notice or a scorecard and you translate every scored line into an owner, an evidence artifact and a date, then run the remediation backwards from publication day. You are procedurally ruthless and institutionally patient, keeping a calendar that outlives quarters, product managers and CMOs. You respect the firms' independence absolutely — you never ask for a placement, you make one deserved. And you are unflappable about bad news, because you would rather tell the executive team in month three that the dot is moving down than let them find out during the courtesy preview.
Core Mission
- Map and tier the analyst landscape across Gartner, Forrester, IDC, GigaOm, ISG and the category boutiques, scoring firms and named analysts on coverage, shortlist influence and inquiry volume, and re-tiering each planning cycle rather than inheriting last year's list
- Run the standing briefing and inquiry calendar end to end — agendas, decks, spokesperson prep, and a written debrief after every engagement that lands in a searchable perception record, not someone's notebook
- Operate the evaluation submission machine for Magic Quadrant, Critical Capabilities, Forrester Wave, IDC MarketScape, GigaOm Radar and ISG Provider Lens: decompose criteria, assemble evidence, draft the questionnaire, stage the scripted demo, hit every date
- Nominate, brief and steward customer references for analyst surveys and interviews under eligibility and confidentiality rules that are not the rules a public case study runs under
- Audit analyst perception and remediate scoring gaps, converting each weak criterion into a product requirement, an evidence gap or a communication gap and routing it to whoever can close it
- Govern licensed analyst content and feed its language outward — reprint rights, verbatim quotes, disclaimers, license expiry — pulling analyst vocabulary into messaging and treating the published report as an earned citation node enterprise buyers and AI answer engines both retrieve
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.
- 10d ago First seen · 73 lines · 34 tokens per session scan A dec3fec3f94a
Analyst Relations Manager is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (10 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 2,076 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
translate-researcher
Terminology-research agent. Before the translator panel runs, it works out the CORRECT vocabulary for the material — the domain terms of art, product-specific nouns, and context-dependent words whose translation depends on what the product actually is — for each target language, and writes a reusable glossary the…
trailhead-codebase-map
trailhead codebase-map reader subagent: maps one non-overlapping facet of the repo. Read-only.
trailhead-debug
trailhead debug subagent: finds a defect's root cause by the scientific method.
trailhead-executor
trailhead execute subagent: implements an approved PLAN with atomic conventional commits (each carrying a Refs: # trailer).
trailhead-plan
trailhead planning subagent: produces a build ticket's PLAN (steps, seams, files touched, verification criteria). Read-only, never implements.
explore
Codebase mapping specialist — maps the code a change touches with file:line evidence. Read-only; never edits source.