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 broadinstitute/fiss-mcp --skill submit-workflow-safelygit clone --depth 1 https://github.com/broadinstitute/fiss-mcpWrote 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/broadinstitute/fiss-mcp/submit-workflow-safely)<a href="https://agentmods.dev/skills/broadinstitute/fiss-mcp/submit-workflow-safely"><img src="https://agentmods.dev/badge/skills/broadinstitute/fiss-mcp/submit-workflow-safely/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/broadinstitute/fiss-mcp/submit-workflow-safely"><img src="https://agentmods.dev/badge/skills/broadinstitute/fiss-mcp/submit-workflow-safely.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 | $0.00029 | $0.01291 |
| Opus 5.5 | $0.00012 | $0.00516 |
| Sonnet 5.5 | $0.00006 | $0.00258 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
submit-workflow-safely 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 27d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Submitting Workflows Safely
This skill teaches you how to verify workflow configuration and safely submit workflows to Terra.
Pre-Submission Checklist
Before submitting a workflow, verify these three things:
1. Verify Method Configuration Points to Correct WDL Version
get_method_config(workspace_namespace, workspace_name, config_namespace, config_name)
Check the methodRepoMethod section for:
methodNamespace: The WDL repository namespacemethodName: The workflow namemethodVersion: The snapshot/version number
Common issue: Configuration points to an old WDL version instead of the latest.
2. Verify Entity Data is Correct
get_entities returns one page (100 rows by default), so never use a bare
call to decide whether an entity exists: on a table with more rows than one
page, a real entity looks missing. Use entity_name, which is an exact lookup
by the table's id, and ask only for the attributes you are about to check.
get_entities(
workspace_namespace, workspace_name, entity_type,
entity_name="<entity_name>",
columns=["<attribute>", "<attribute>"],
)
Do not use filter_terms for this. It is a substring search over the row, so a
miss does not mean the entity is absent. entity_name returns exactly 0 or 1
rows, and 0 is a real answer rather than an error.
Confirm from the response:
countis 1, and the row is inentities- The attributes you need are populated
- File paths (GCS URLs) look right
Attribute names come from get_workspace_data_tables, which lists each table's
columns alongside its row count. Omitting columns returns every attribute
and is refused outright above max_response_bytes on a wide table; see the
manage-context-size skill.
3. Verify Input Mappings are Configured
In the method configuration (from step 1), check:
inputs: Maps WDL input variables to entity attributes or literal valuesoutputs: Maps WDL outputs to entity attributes for storagerootEntityType: Must match the entity type you're submitting
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.
- 27d ago Changed · +16 lines 95fae6fc7996
- 2mo ago First seen · 168 lines · 29 tokens per session scan A 1701bf9c66f3
submit-workflow-safely is a skill published in the GitHub repository broadinstitute/fiss-mcp (6 stars, last pushed 28d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,291 once invoked, about $0.0001 per session on Opus 5.5. 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.
submit-workflow-safely compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| submit-workflow-safelybroadinstitute/fiss-mcp | Skill | 6 | 28d ago | Apache-2.0 | A | 29 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |