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 skills/ericrisco/rsc-harness/project-opsnpx skills add ericrisco/rsc-harness --skill project-opsgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/project-ops)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/project-ops"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/project-ops.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 | $0.00080 | $0.02351 |
| Opus 5 | $0.00040 | $0.01175 |
| Sonnet 5 | $0.00016 | $0.00470 |
| Haiku 4.5 | $0.00008 | $0.00235 |
Grade A, and why
project-ops 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 yesterday.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
project-ops
You run a project from one flat file, not a PM tool. project-ops is the operational layer above a plan: a short list of dated milestones, each with a single accountable owner and a binary done-test; a RAG status set by rules instead of vibes; a RAID log running alongside; early detection when something is trending late; and a weekly status report a stakeholder reads in under two minutes. Your job is to never let a board where "everything is green" hide a milestone that is two weeks from missing. You do not sequence engineering tasks (that is ../tasks/SKILL.md) and you do not write the architecture plan (that is ../plan/SKILL.md) — you keep the whole project honest above both.
The artifact comes first
Before any process, there is one file. Everything else updates it. A milestone table:
| id | milestone | owner | target | status | done_test | depends_on |
|----|-----------|-------|--------|--------|-----------|------------|
| M1 | Pricing copy approved | @ana | 2026-06-10 | done | Final copy signed off in doc | |
| M2 | Pricing page built | @ben | 2026-06-18 | amber | URL returns 200 with new copy | M1 |
| M3 | Page live in prod | @ben | 2026-06-24 | green | prod URL 200, analytics firing | M2 |
Columns are a fixed contract — id | milestone | owner | target | status | done_test | depends_on. CSV with the same header is equivalent and is what scripts/verify.sh lints. This file is the single source of truth; the status report is a view of it, never a second copy that drifts.
Rules for the contract, each with its why:
idis unique and stable —depends_onreferences it, so renaming breaks the graph.owneris exactly one person, with an@handle— "accountability without a named owner defaults to no accountability." Never a team (@marketing) or two people.targetis an ISO date (YYYY-MM-DD) — so "trending late" is arithmetic, not opinion.statusis one of{green, amber, red, done}— a closed set the report and the linter both trust.done_testis binary and verifiable — you can point at it and say yes/no, no "improve" or "work on".depends_onis a comma-separated list of real ids — the dependency edges that reveal the critical path.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 131 lines · 80 tokens per session scan A 478e821db4f7
project-ops is a skill published in the GitHub repository ericrisco/rsc-harness (64 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 2,351 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.
hns-workflow-ci-loop
Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user. Use for CI loop workflow — NOT for general loop iteration patterns (see…
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
moai-harness-learner
Harness learning subsystem coordinator. Produces Tier 4 auto-update proposal payloads consumed by the orchestrator (which surfaces them via AskUserQuestion) and orchestrates Apply/Rollback flows. Triggers when harness learning proposals are pending or learning lifecycle management is needed.
moai-workflow-thinking
Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.