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 skills add magnus919/agent-skills --skill technical-project-managementgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/technical-project-management)<a href="https://agentmods.dev/skills/magnus919/agent-skills/technical-project-management"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/technical-project-management/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/skills/magnus919/agent-skills/technical-project-management"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/technical-project-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 149 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00163 | $0.02348 |
| Opus 5 | $0.00081 | $0.01174 |
| Sonnet 5 | $0.00033 | $0.00470 |
| Haiku 4.5 | $0.00016 | $0.00235 |
Grade A, and why
technical-project-management 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 6d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Project Management
Help a team make and maintain credible delivery commitments. Start at the user's current decision; do not restart a healthy project or impose a new methodology.
First move
Read existing project artifacts before asking questions. Identify the outcome, current phase, immediate decision, decision-maker, constraints, and evidence gaps. Infer experience from the request and artifacts; ask about preference only if it matters. For teams without a PM, provide a small usable working system and explain unfamiliar concepts in context. For experienced TPMs, lead with the delta, options, recommendation, and decision needed; omit introductory lessons.
Choose the entry point
| Starting condition | First action | Primary output |
|---|---|---|
| New or inherited project with unclear mandate | Read Engagement and initiation | Proposed brief with authority and evidence gaps |
| Approved work with a delivery method but weak control | Read Control and communication | Current control record and decision brief |
| Slipping date, cost, scope, or dependency | Read Forecasting and schedule analysis and Change and recovery | Conditional forecast and recovery options |
| Cross-team, supplier, or mixed-method handoff | Read Hybrid and dependencies | Dependency agreement and acceptance evidence |
| Delivered work, retirement, or decommissioning with unresolved ownership or benefits | Read Closure and transition | Conditional closure, accepted transition, or decommissioning record |
| Technical uncertainty needs staged learning | Read Adaptive delivery | Evidence-backed decision among PoC, prototype, pilot, or stop; none alone proves production readiness |
| Forecast, deadline, or resource-feasibility question | Read Forecasting and schedule analysis | Conditional forecast stating model, assumptions, capacity, and feasibility limits |
| Material risk, issue, assumption, or decision needs control | Read Control and communication | Record with owner, signal/trigger, response, authority, and next review |
| A supplier or team handoff lacks readiness or acceptance evidence | Read Hybrid and dependencies | Agreement with provider, receiver, definition of ready, evidence, fallback, and escalation |
What ships with it
35 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.
- evals/evals.json 8.6 KB
- evals/sample-review.md 3.8 KB
- evals/samples/baseline-expert.md 2.2 KB
- evals/samples/baseline-schedule.md 1.4 KB
- evals/samples/baseline-team.md 2.2 KB
- evals/samples/final-team-provenance.json 789 B
- evals/samples/final-team.md 4.6 KB
- evals/samples/with-skill-expert.md 2.5 KB
- evals/samples/with-skill-schedule.md 1.9 KB
- evals/samples/with-skill-team.md 3.6 KB
- README.md 2.3 KB
- references/adaptive-delivery.md 3.2 KB
- references/case-studies.md 4.1 KB
- references/change-and-recovery.md 3.5 KB
- references/closure-and-transition.md 2.5 KB
- references/control-and-communication.md 3.5 KB
- references/engagement-and-initiation.md 3.5 KB
- references/evaluation-guide.md 2.9 KB
- references/flow-and-capacity.md 2.9 KB
- references/forecasting.md 4.9 KB
- references/hybrid-and-dependencies.md 3.3 KB
- references/method-selection.md 4.1 KB
- references/predictive-and-stages.md 3.0 KB
- references/research-brief.md 3.9 KB
- references/source-index.md 6.1 KB
- scripts/schedule.py 7.3 KB runs code
- scripts/test_schedule.py 6.7 KB runs code
- templates/approach-decision.md 1.1 KB
- templates/change-and-recovery.md 1.1 KB
- templates/closure-record.md 1.0 KB
- templates/dependency-agreement.md 854 B
- templates/project-brief.md 1.5 KB
- templates/project-control.md 1.5 KB
- templates/schedule-example.json 400 B
- templates/status-and-decision.md 920 B
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.
- 6d ago First seen · 161 lines · 163 tokens per session scan A e389237f52fa
technical-project-management is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 163 tokens to every session and 2,348 once invoked, about $0.0008 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 2026-09-06.
Other skills, from other repositories
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
plan
Enter the Plan phase of CocoBrew. Runs CocoSpec quality gate pre-flight, reads spec.md and discuss.md (if present), invokes Coco native plan mode as a mandatory gate, captures the approved plan to plan.md, creates initial flow.json template, and commits. Must have $spec completed first.
cocoplus-config
CocoPlus configuration SSOT — $cocoplus sync propagates cocoplus.toml into downstream artifacts; $cocoplus migrate-config converts legacy safety-config.json. Invoked via $cocoplus sync and $cocoplus migrate-config.
ops-demo
CocoOps demo mode activator — populates .cocoplus/ops/demo/ with realistic mock data and sets cocoplus.toml [demo] enabled = true. Invoked via $ops demo.
ops-dora
CocoOps DORA metrics — computes four DORA-adapted delivery metrics from Snowflake task history and git log. Extends the longitudinal delivery thesis through the skill-native CocoOps thesis workflow. Invoked via $ops dora.
ops-sprint
CocoOps sprint health — computes story velocity, burndown, and completion prediction from git log and sprint window config. Invoked via $ops sprint.