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/adrian-d-hidalgo/nestjs-mcp-server/developgit clone --depth 1 https://github.com/adrian-d-hidalgo/nestjs-mcp-serverWrote 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/commands/adrian-d-hidalgo/nestjs-mcp-server/develop)<a href="https://agentmods.dev/commands/adrian-d-hidalgo/nestjs-mcp-server/develop"><img src="https://agentmods.dev/badge/commands/adrian-d-hidalgo/nestjs-mcp-server/develop.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.03839 |
| Opus 5 | $0.00045 | $0.01920 |
| Sonnet 5 | $0.00018 | $0.00768 |
| Haiku 4.5 | $0.00009 | $0.00384 |
Grade A, and why
develop 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 4d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope is local development only — no merge, no release, no publish.
/specification already decided what must be built and how it will be verified:
.project/tasks/issue-<N>/spec.md and test-plan.md. /develop decides how, concretely, against
this working tree and then does it. It executes against the SPEC; it does not re-derive the
technical analysis and it never edits spec.md — a wrong SPEC is a /specification refine, not
something to bend the work around.
The execution plan is ephemeral. It lives in this conversation and is not written to disk. It is
specific to the working tree in front of you and stale the moment the code moves; a stale plan on
disk is worse than none, because a later session reads it as current. What persists from this
command is the evidence: verification.md and notes.md.
This command also performs the verification that Caperifai splits into a separate /test stage:
the QA plan is executed and the issue's full acceptance criteria are recorded before anything is
declared ready to commit.
For anything unclear — an acceptance criterion whose success signal is undefined, a SPEC claim the current code contradicts — emit questions or verify against the code. Never invent a file, a dependency, or a plan detail to fill a gap.
Scope discipline (hard). The plan and the execution cover EXACTLY the issue's scope — what it
implies, nothing more. developer does not extend into another issue's work, however incomplete the
whole looks without it. If something critical to this issue's own delivery is missing, it is
surfaced as a blocker and appended to notes.md — never silently built. Getting creative and
implementing the neighbouring piece is the failure this guards against.
Phase 1 — Plan (in-session; stops for your approval)
- Check preconditions.
issue_readthe issue and its comments.-
No
spec.mdin.project/tasks/issue-<N>/→ stop and point at/specification <#N>. The technical analysis belongs there. Prepare nothing. Note that the issue itself will show no sign of whether a SPEC exists — nothing is ever written to it — so the workspace is the only place to check, and an absentspec.mdmeans either the SPEC was never written or the workspace lives on another machine. Either way, do not improvise the analysis here. -
Blocked by #Nunresolved → stop and report. -
Bug issue with no root cause → stop and point at
/debug <#N>. -
The SPEC declares itself not ready → stop. Read the
**Status:**field, whichtemplates/SPEC.mdrequires on the third line:grep -m1 '^\*\*Status:\*\*' .project/tasks/issue-<N>/spec.mdready→ continue.blocked: <question>→ stop and report the question. Missing → treat asblockedand say the SPEC predates the field, rather than assuming either way.A SPEC is allowed — and expected — to conclude that a requirement admits several materially different designs and that the choice was never made. When it says so, the missing piece is a decision, not code. Building anyway means inventing the design the SPEC deliberately refused to invent, and doing it inside an execution plan, where it reads as settled.
-
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.
- 4d ago First seen · 235 lines · 90 tokens per session scan A c9cae9d0955e
develop is a command published in the GitHub repository adrian-d-hidalgo/nestjs-mcp-server (38 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 3,839 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.
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.