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 agentmods add commands/d-padmanabhan/agent-engineering-handbook/bashgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWhat 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 | $0.00014 | $0.00735 |
| Opus 5 | $0.00007 | $0.00367 |
| Sonnet 5 | $0.00003 | $0.00147 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
bash scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Network calls**: if using `curl`, apply the `140-bash.mdc` “Curl in scripts” baseline (timeouts + retries). How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BASH MODE ACTIVATED
You are now in BASH MODE. Any work on Bash scripts MUST follow:
rules/140-bash.mdc(Bash Engineering Ruleset)rules/100-core.mdc(minimal, secure, production-ready)rules/310-security.mdc(no secrets, OWASP-minded)
This command is used when the user asks Cursor to:
- Generate a new Bash script
- Modify an existing Bash script
- Review an existing Bash script
Guardrails (mandatory)
- No secrets: never add tokens/keys/passwords to scripts or examples.
- Quoting: quote variables and paths (
"${var}"), unless word splitting is explicitly intended. - No
evalwith user input. - No parsing
lsoutput. - Safe temp files: prefer
mktemp+trapcleanup. - Network calls: if using
curl, apply the140-bash.mdc“Curl in scripts” baseline (timeouts + retries). - Examples: use
acme.comdomains for examples.
Step 0: Determine intent (create vs modify vs review)
Infer intent from the user’s request. If ambiguous, ask ≤3 clarifying questions that materially change the implementation (e.g., target OS, required inputs/outputs, whether retries are expected).
Create: generate a new script
Produce a complete, runnable script (no TODO stubs) with:
- Shebang:
#!/usr/bin/env bash(default) - Safety mode: choose and justify
set -euo pipefailvsset -uo pipefail main()entrypoint +usage()(when args are non-trivial)- Dependency checks:
command -v - Logging helper (UTC timestamps) to stderr
- Structured error handling (traps) when warranted
shellcheck-clean,shfmt-formatted output
If the script talks to an HTTP API:
- Use the
curlbaseline options pattern fromrules/140-bash.mdc - Do not log auth headers/tokens
Modify: change an existing script
Follow “minimal diff” discipline:
- Preserve behavior unless the user asked to change it
- Don’t refactor unrelated parts
- Keep changes localized and reversible
- If changing error-handling mode, explain why
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.
- 2d ago First seen · 89 lines · 14 tokens per session scan A 3f641a2187e8
bash is a command published in the GitHub repository d-padmanabhan/agent-engineering-handbook (15 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 735 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.