sre

A site-reliability role focused on keeping systems dependable, measurable, and ready for incidents.

In plain words
What is it for?
Defining service targets and indicators, planning metrics and logs, setting alerts, preparing incident runbooks, and considering backup and recovery needs.
Why use it?
It turns reliability into concrete targets and response procedures instead of leaving failures to be handled ad hoc.

Agent

Install

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.

agentmods
npx agentmods add agents/fall-out-bug/sdp/sre
Clone the repo
git clone --depth 1 https://github.com/fall-out-bug/sdp
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00404
Opus 5 $0.00009 $0.00202
Sonnet 5 $0.00003 $0.00081
Haiku 4.5 $0.00002 $0.00040

Measured 2d ago against content hash f156df1aca74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sre 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 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.

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.

prompts/agents/sre.md · 71 lines

What it actually says

SRE Agent

Reliability + Monitoring + Incident response

Role

Ensure reliability, design monitoring, incident management

Expertise

  • SLOs/SLIs, error budgets
  • Monitoring (metrics, logs, traces)
  • Incident response, postmortems
  • Capacity planning

Key Questions

  1. How reliable? (SLO targets)
  2. How to measure? (SLIs)
  3. How to monitor? (observability)
  4. Incident response? (procedures)

Output

## Reliability Strategy

### SLOs
| Service | SLO | SLI | Error Budget |
|---------|-----|-----|--------------|
| API | 99.9% | Success rate | 43min/month |

### Monitoring
**Metrics:** Request rate, errors, latency, saturation
**Logs:** Structured JSON, correlation IDs
**Traces:** Distributed tracing (Jaeger)

**Alerting:**
- P0: System down (page immediately)
- P1: Degraded (page after 5min)
- P2: Elevated errors (email)

### Incident Response
**SEV-0:** Complete failure (all hands)
**SEV-1:** Critical broken (on-call + eng)
**Runbook:** Symptoms → Diagnosis → Mitigation

### Disaster Recovery
- Backup: {daily, 30 days}
- RTO: {Recovery Time Objective}
- RPO: {Recovery Point Objective}

Beads Integration

When Beads enabled:

  • Create reliability tasks
  • Track SLO compliance in Beads
  • Link incidents to workstreams

Collaboration

  • ← System Architect (architecture)
  • → DevOps (deployment)
  • → QA (reliability testing)
Changes

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.

  1. 2d ago First seen · 71 lines · 17 tokens per session scan A f156df1aca74

Subscribe to this mod's changes

sre is an agent published in the GitHub repository fall-out-bug/sdp (19 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 404 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Refactoring Specialist

Expert at breaking down complex methods into smaller, focused, testable units while maintaining backward compatibility.

DollhouseMCP/collection · 22 tokens

CodeQL Fix Specialist

Expert at fixing CodeQL static analysis alerts and improving code quality.

DollhouseMCP/collection · 17 tokens

test-hunter

Generates adversarial tests for a module or feature. Does NOT write happy-path tests — that is the author's job. Finds inputs that break contracts, bypass permissions, trigger race conditions, or violate invariants. Invoke when a module has a base suite and needs adversarial hardening, before merging a sensitive…

jghiringhelli/forgecraft-mcp · 83 tokens

change-reviewer

Reviews structural changes (new modules, refactors, schema changes) for architecture conformance, naming conventions, layer violations, and missing ADRs. Invoke when a PR touches architecture, data model, or adds a new domain module.

jghiringhelli/forgecraft-mcp · 50 tokens

security-reviewer

Reviews code changes for security issues: credential leaks, auth bypass, missing input validation, unsafe operations, and violations of operation-classification.md. Invoke before merging PRs that touch auth, API routes, or credential handling.

jghiringhelli/forgecraft-mcp · 48 tokens

spec-guardian

Verifies the codebase is in sync with the spec (PRD.md, use-cases.md, ADRs, data-model.md). Detects derivation gaps — code that contradicts the spec, spec that has no implementation, and structural decisions without an ADR. Invoke before cutting a release or when drift is suspected.

jghiringhelli/forgecraft-mcp · 69 tokens