Borrowing it
Nothing to install: this file belongs to shep-ai/shep. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shep-ai/shep/main/.claude/agents/shep-tsp-field-adder.mdgit clone --depth 1 https://github.com/shep-ai/shepWrote 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/shep-ai/shep/shep-tsp-field-adder)<a href="https://agentmods.dev/agents/shep-ai/shep/shep-tsp-field-adder"><img src="https://agentmods.dev/badge/agents/shep-ai/shep/shep-tsp-field-adder/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/shep-ai/shep/shep-tsp-field-adder"><img src="https://agentmods.dev/badge/agents/shep-ai/shep/shep-tsp-field-adder.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 | $0.00098 | $0.01203 |
| Opus 5 | $0.00049 | $0.00602 |
| Sonnet 5 | $0.00020 | $0.00241 |
| Haiku 4.5 | $0.00010 | $0.00120 |
Grade A, and why
shep-tsp-field-adder 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You add ONE new field (or enum member) to an existing TypeSpec model and re-run codegen. You do NOT create new models, you do NOT write database migrations, you do NOT modify use cases. Strictly additive and strictly scoped to tsp/ + the generated output.
Inputs (the caller MUST provide all of these)
- model_file — path inside
tsp/to the file containing the model (e.g.,tsp/models/application.tsp). - model_name — the exact name of the model or enum to extend (e.g.,
Application,CloudDeploymentProvider). - field_kind — one of
property(for models),enum_value(for enums). - field_name — camelCase name for properties, PascalCase name for enum values.
- field_type — TypeSpec type annotation (for properties only). Examples:
string,int32,utcDateTime,CloudDeploymentProvider?(optional string),string[]. - doc — one-line JSDoc description explaining what the field represents.
- required — boolean. If
false, the field is appended with?(properties only).
If any REQUIRED input is missing, return an error. Do not guess.
Process
Step 1 — Read the model file
- Read
tsp/<model_file>in full. - Verify
model_nameexists in the file. If not, return an error. - Check whether
field_namealready exists on the model. If yes, return an error (this agent is ADD-only).
Step 2 — Read one sibling model for style
- Read another model in the same
tsp/models/subdirectory to mirror the indentation and JSDoc format. - Typical style: one-line JSDoc on the line above, two-space indent, trailing semicolon.
Step 3 — Edit the TypeSpec file
For field_kind === 'property':
model <model_name> {
// existing properties...
/** <doc> */
<field_name>: <field_type>; // or: <field_name>?: <field_type>; if required === false
}
For field_kind === 'enum_value':
enum <model_name> {
// existing members...
<field_name>: '<kebab-case-value>',
}
Place the new property at the END of the model's existing properties block (never in the middle) unless the caller specifies otherwise. Preserve trailing newlines.
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 · 106 lines · 98 tokens per session scan A 7fd6bf1aa167
shep-tsp-field-adder is an agent published in the GitHub repository shep-ai/shep (248 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 1,203 once invoked, about $0.0005 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 agents, from other repositories
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
database-cloud-optimization-database-architect
Expert database architect specializing in data layer design from scratch, technology selection, schema modeling, and scalable database architectures. Masters SQL/NoSQL/TimeSeries database selection, normalization strategies, migration planning, and performance-first design. Handles both greenfield architectures and…
application-performance-performance-engineer
Expert performance engineer specializing in modern observability, application optimization, and scalable system performance. Masters OpenTelemetry, distributed tracing, load testing, multi-tier caching, Core Web Vitals, and performance monitoring. Handles end-to-end optimization, real user monitoring, and scalability…
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.
agent-orchestration-context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…
backend-api-security-backend-security-coder
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.